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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11063
    Prev
    Next
    INDEX
    Explanations

    C-style code, including `fprintf`, `fcntl`, and bitwise OR operators

    oai_token-act-pair · gemini-2.0-flash

    words related to error messages in programming

    np_token-act-pair-logits · gpt-4o-mini

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     onOptions
    -0.62
    dehydes
    -0.49
    isantes
    -0.48
    entran
    -0.48
    TryGetValue
    -0.47
     GenerationType
    -0.47
     kaarangay
    -0.47
     olen
    -0.47
    oprot
    -0.45
    entra
    -0.45
    POSITIVE LOGITS
    saraba
    0.63
    يميديا
    0.63
    exitRule
    0.58
    Население
    0.56
    CppMethod
    0.54
    Hochspringen
    0.54
    خصة
    0.52
     regioni
    0.52
     policiers
    0.51
    AndEndTag
    0.50
    Activations Density 1.648%

    No Known Activations