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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16340
    Prev
    Next
    INDEX
    Explanations

    code syntax like semicolons or parenthesis inside C or PHP code blocks

    oai_token-act-pair · gemini-2.0-flash

    say "};"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    AccessorTable
    -0.58
     AssemblyCulture
    -0.56
    хьтан
    -0.55
    Personendaten
    -0.54
    رشف
    -0.54
    ipedi
    -0.54
    ItemBackground
    -0.53
     kasarigan
    -0.53
     الرياضيه
    -0.52
     архивлан
    -0.50
    POSITIVE LOGITS
    záll
    0.59
    nty
    0.59
    asons
    0.59
     actionTypes
    0.54
     Sitten
    0.53
    parr
    0.53
    stwo
    0.51
    httphttps
    0.51
     Reserved
    0.50
    rdata
    0.50
    Activations Density 5.155%

    No Known Activations