Abstract Predicting T cell receptor (TCR) specificity on the basis of sequence is challenging because TCRs of similar sequence can recognize entirely different antigens, whereas TCRs of different sequence can recognize the same antigens. Here we present a system that integrates high-throughput yeast display with fine-tuned protein language models (pLMs) to generate deep peptide recognition profiles (PRPs) for individual TCRs, each detailing binding against millions of peptides. We provide detailed PRPs for a panel of HLA-B*27:05-restricted TCRs from persons with ankylosing spondylitis and acute anterior uveitis that almost exclusively recognize peptides through CDR3β. pLMs trained on these PRPs outperform AlphaFold3 and tFold-TCR in predicting T cell activation. We discover and validate novel candidate autoantigens, demonstrate that model generalization to new TCRs correlates with functional distance (PRP divergence) rather than sequence similarity and introduce a model-intrinsic uncertainty metric to quantify prediction confidence. This system and its associated PRP datasets offer a scalable approach to mapping TCR recognition, accelerating antigen discovery and guiding TCR engineering. Similar content being viewed by others Main T cell receptors (TCRs) recognize a composite surface composed of antigenic peptide and major histocompatibility complex (pMHC) molecules1. Interrogation of pMHC complexes by the TCR underpins adaptive immunity, orchestrating responses to pathogens, cancer and autoimmunity2,3. However, the structural complexity of the TCR–pMHC interface presents both challenges and opportunities for biotechnological intervention4. A fundamental paradox of TCR recognition is that TCRs with little to no sequence similarity can bind the same pMHC, while nearly identical TCRs can exhibit distinct specificities5,6. Consequently, sequence-based clustering methods such as GLIPH and TCRdist capture broad statistical trends in epitope specificity5,7. However, they are limited in resolving fine-grained specificity among closely related TCRs. Current approaches to bridge this sequence–function gap face notable limitations8,9,10. While high-throughput experimental techniques such as yeast or mammalian display can map peptide