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. 5869
    Prev
    Next
    INDEX
    Explanations

    citation references within a scientific document

    oai_token-act-pair · gemini-2.0-flash

    citation references or academic sources

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

    Academic paper references

    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
    RegressionTest
    -0.68
    цездатний
    -0.64
    исленность
    -0.64
     nitrates
    -0.63
    styrelsen
    -0.62
    gnition
    -0.61
    amsmath
    -0.60
    oredCriteria
    -0.59
    jspx
    -0.57
    TypedDataSet
    -0.57
    POSITIVE LOGITS
     EconPapers
    0.53
     daf
    0.47
     Vedi
    0.46
    geable
    0.45
     prec
    0.44
    NB
    0.44
    ExecuteReader
    0.43
     ویکی‌پدیای
    0.42
    kı
    0.42
    Примечания
    0.42
    Activations Density 4.088%

    No Known Activations