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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5965
    Prev
    Next
    INDEX
    Explanations

    words related to the fundamentals, basis, or theory for something

    oai_token-act-pair · gemini-2.0-flash

    terms related to foundational concepts or principles

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

    foundation

    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
     disambiguazione
    -0.76
    دانشنامهٔ
    -0.61
    twimg
    -0.57
    verwijspagina
    -0.55
    Personendaten
    -0.55
    titleMargin
    -0.53
    uxxxx
    -0.53
    OrNil
    -0.52
     }{@
    -0.52
     autorytatywna
    -0.52
    POSITIVE LOGITS
     jegy
    0.58
    исленность
    0.57
     Arquivado
    0.56
     Roskov
    0.56
     from
    0.55
    Slf
    0.52
     exemplaire
    0.51
    Ņ
    0.51
    dumb
    0.51
    CodeAttribute
    0.50
    Activations Density 15.865%

    No Known Activations