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. 16363
    Prev
    Next
    INDEX
    Explanations

    words related to symbols, letters, and names

    oai_token-act-pair · gemini-2.0-flash

    the letter [any capital letter]

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

    About written language

    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
    verwijspagina
    -1.14
    RenderAtEndOf
    -1.06
     متعلقه
    -1.00
     Theſe
    -0.94
     disambiguazione
    -0.93
     auffi
    -0.92
     Majefty
    -0.91
    InputBorder
    -0.91
     pleaſure
    -0.91
     protoimpl
    -0.90
    POSITIVE LOGITS
     M
    0.78
     C
    0.73
     T
    0.73
     S
    0.72
     D
    0.69
     P
    0.68
     L
    0.65
     G
    0.63
     B
    0.63
     N
    0.63
    Activations Density 0.886%

    No Known Activations