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. 1728
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    -1.43
    ",
    -1.16
    ),
    -1.08
    </
    -0.90
    ”,
    -0.86
    ',
    -0.84
    —
    -0.70
    :
    -0.69
    “
    -0.65
    :],
    -0.65
    POSITIVE LOGITS
    −
    0.63
    ['
    0.62
     Normdatei
    0.62
    [],
    0.60
    StoreMessageInfo
    0.59
    NewUrlParser
    0.59
    FieldBuilder
    0.59
    {\
    0.57
    DeleteBehavior
    0.56
    @"
    0.55
    Activations Density 8.923%

    No Known Activations