© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 14036
    Prev
    Next
    INDEX
    Explanations

    the token "pat", often related to medical patents or patients in a healthcare setting

    oai_token-act-pair · gemini-2.0-flash

    pat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Pat
    -2.63
     pat
    -2.59
    Pat
    -2.56
    pat
    -2.48
    PAT
    -1.94
     PAT
    -1.94
     patent
    -1.15
    pats
    -1.15
     pats
    -1.13
     Patt
    -1.13
    POSITIVE LOGITS
     Theſe
    0.53
     varandra
    0.52
     théorie
    0.52
    !='
    0.51
     fevere
    0.50
    ]='\
    0.49
     télécommande
    0.49
    }}^{(
    0.49
     prefent
    0.48
    pantalón
    0.48
    Activations Density 1.159%

    No Known Activations