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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16268
    Prev
    Next
    INDEX
    Explanations

    legal and scientific text patterns

    oai_token-act-pair · gemini-2.0-flash

    code-related text

    np_token-act-pair-logits · gemini-2.0-flash

    random assortment of texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
    XmlEnum
    -0.60
    windowFixed
    -0.57
     الحره
    -0.54
     both
    -0.48
     neither
    -0.48
    wery
    -0.47
    Datuak
    -0.47
    itis
    -0.47
     either
    -0.46
     par
    -0.45
    POSITIVE LOGITS
    ViewImports
    0.79
    +#+
    0.75
     صوتيه
    0.72
    onViewCreated
    0.72
    migrationBuilder
    0.69
     GenerationType
    0.66
     referrerpolicy
    0.66
    tvguidetime
    0.63
    !("{}",
    0.63
    GOTREF
    0.62
    Activations Density 0.543%

    No Known Activations