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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1557
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, especially numbers and symbols representing numerical quantities

    oai_token-act-pair · gemini-2.0-flash

    scientific formulas and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     Efq
    -1.08
     houſe
    -1.02
     ſever
    -1.00
     myſelf
    -0.98
     Monfieur
    -0.97
     purpoſe
    -0.95
     itſelf
    -0.95
     ſte
    -0.94
     himſelf
    -0.93
     Jefus
    -0.92
    POSITIVE LOGITS
    twimg
    0.56
    +$
    0.53
    }^{*}(
    0.52
    \}=
    0.52
    :+
    0.50
    ^{*}=
    0.50
    |>
    0.50
    +}
    0.50
    ^{-}$
    0.50
    isContained
    0.49
    Activations Density 4.102%

    No Known Activations