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. 11121
    Prev
    Next
    INDEX
    Explanations

    LaTeX code snippets

    oai_token-act-pair · gemini-2.0-flash

    LaTeX syntax and commands

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

    LaTeX code

    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
    DRV
    -0.55
     stanovnika
    -0.47
     empre
    -0.46
    +:+
    -0.44
     De
    -0.44
     Cullen
    -0.43
    wapV
    -0.41
    Cana
    -0.41
     bell
    -0.41
    ñan
    -0.41
    POSITIVE LOGITS
     nahilalakip
    0.84
    AndEndTag
    0.81
     kaynağından
    0.71
     <=",
    0.59
     للاسماء
    0.59
     NUKAT
    0.58
    KommentareTeilen
    0.57
    RectangleBorder
    0.56
    Chham
    0.54
    DoubleQuotes
    0.54
    Activations Density 1.372%

    No Known Activations