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. 5850
    Prev
    Next
    INDEX
    Explanations

    words indicating a condition or state of being, or an assessment of quality

    oai_token-act-pair · gemini-2.0-flash

    uncommon or foreign words and phrases

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

    Adverbs

    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
    ValueStyle
    -0.70
    nocześnie
    -0.57
     kuitenkin
    -0.55
     Infatti
    -0.55
    RectangleBorder
    -0.53
    šinou
    -0.53
    AnimationsModule
    -0.52
     vícti
    -0.52
    enumii
    -0.52
     ändå
    -0.51
    POSITIVE LOGITS
     تضيفلها
    0.63
    imageshack
    0.61
    +#+
    0.61
    ◀
    0.60
     désolés
    0.59
    Seine
    0.55
     ProtoMessage
    0.55
    cyklopedia
    0.52
     possible
    0.50
    kmale
    0.50
    Activations Density 11.155%

    No Known Activations