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. 1710
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers associated with NOTE attributes

    oai_token-act-pair · gemini-2.0-flash

    0

    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
     Viceroy
    -0.55
     Manchuria
    -0.52
     Iroquois
    -0.52
     Ancona
    -0.50
     Cicero
    -0.50
     mirth
    -0.49
     auricular
    -0.49
     Girona
    -0.49
     spiro
    -0.49
     IMS
    -0.49
    POSITIVE LOGITS
    دانشنامهٔ
    0.65
    FFFF
    0.63
    fdb
    0.55
    xE
    0.54
    xfa
    0.54
    /#{
    0.54
    fef
    0.54
    xbe
    0.53
    })).
    0.53
    ceae
    0.53
    Activations Density 12.119%

    No Known Activations