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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14268
    Prev
    Next
    INDEX
    Explanations

    DNA sequences and other genetic markers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
     Kan
    -0.63
    Kan
    -0.59
     kan
    -0.59
    кана
    -0.58
     Abre
    -0.56
    Kand
    -0.56
     cand
    -0.55
     kre
    -0.54
     ACT
    -0.53
     KAN
    -0.52
    POSITIVE LOGITS
     Normdatei
    1.04
     كومونز
    0.87
    RectangleBorder
    0.81
    rrggbb
    0.78
    PreferredItem
    0.77
    cote
    0.77
     Coz
    0.77
     Cof
    0.76
    OGND
    0.76
     COP
    0.76
    Activations Density 0.293%

    No Known Activations