Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16306
    Prev
    Next
    INDEX
    Explanations

    statistical data that relates numbers, prepositions, and measures

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     von
    -0.59
     a
    -0.57
    ,
    -0.54
    <eos>
    -0.54
     F
    -0.53
     A
    -0.53
     M
    -0.53
     (
    -0.52
    ↵↵
    -0.51
     the
    -0.51
    POSITIVE LOGITS
     itſelf
    1.19
     myſelf
    1.10
     Shakspeare
    1.09
     Efq
    1.08
     ―――――
    1.06
     Audiodateien
    1.03
    )";
    
    1.03
     Chriftian
    1.01
     raiſ
    0.99
     Monfieur
    0.99
    Activations Density 4.178%

    No Known Activations