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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11145
    Prev
    Next
    INDEX
    Explanations

    parenthetical statements containing taxonomic information related to algae

    oai_token-act-pair · gemini-2.0-flash

    programming terminology

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

    Code/computer terms

    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
     lèvres
    -0.50
     survie
    -0.49
     Polskiego
    -0.49
     fenó
    -0.48
    Revenir
    -0.48
    bní
    -0.47
     rivista
    -0.47
    Merk
    -0.47
    hidup
    -0.46
     montagna
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.63
    DockStyle
    0.62
    webElementXpaths
    0.59
    aarrggbb
    0.58
    ]='\
    0.57
    migrationBuilder
    0.56
    WriteBarrier
    0.56
    enderror
    0.56
    EndInit
    0.55
    GEBURTSDATUM
    0.55
    Activations Density 5.404%

    No Known Activations