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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16247
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and functions with associated syntax

    oai_token-act-pair · gemini-2.0-flash

    mathematical functions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     Asylum
    -0.54
     exud
    -0.51
    kać
    -0.49
     SECRETARY
    -0.46
     quirúrg
    -0.46
     Beb
    -0.46
     Secretary
    -0.46
     contact
    -0.45
    padu
    -0.44
     selling
    -0.43
    POSITIVE LOGITS
    DoubleQuotes
    0.70
    AndEndTag
    0.69
    Composable
    0.66
     صوتيه
    0.66
    atrième
    0.64
    UnknownFieldSet
    0.61
    AsUp
    0.60
    rensa
    0.58
    QMetaType
    0.57
    FailureListener
    0.54
    Activations Density 6.660%

    No Known Activations