© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9262
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mortimer
    0.63
    тури
    0.60
    acol
    0.59
    тяги
    0.59
    ালিক
    0.59
    鳌
    0.57
    னிய
    0.57
     Seymour
    0.57
     হোমিওপ্যাথিক
    0.56
    ीडी
    0.56
    POSITIVE LOGITS
     জন্
    0.60
    应用的
    0.58
     同时
    0.56
     doğ
    0.56
    現在は
    0.56
     skriv
    0.56
     waste
    0.56
     Genomic
    0.55
     குறைவாக
    0.55
     腰
    0.54
    Activations Density 0.001%

    No Known Activations