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. 5880
    Prev
    Next
    INDEX
    Explanations

    a mix of programming code, Spanish words/phrases and references to academic papers.

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'yo' or similar phonetic patterns

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

    greetings

    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
     surla
    -0.66
    antMatchers
    -0.57
    contentLoaded
    -0.56
    ulents
    -0.54
    UnknownFieldSet
    -0.52
     بيها
    -0.52
     AssemblyProduct
    -0.52
    abetes
    -0.51
    matchCondition
    -0.51
    CompleteListener
    -0.51
    POSITIVE LOGITS
    yo
    0.81
    jo
    0.77
    Uo
    0.76
    io
    0.74
    go
    0.73
    GO
    0.68
    JO
    0.68
    YO
    0.66
    ئو
    0.66
    Io
    0.66
    Activations Density 2.560%

    No Known Activations