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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16222
    Prev
    Next
    INDEX
    Explanations

    undefined behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
     P
    0.41
     باستخدام
    0.40
     vám
    0.39
    和一个
    0.38
    ↵↵↵↵↵↵↵
    0.38
     ولكن
    0.37
    itzar
    0.37
     dien
    0.37
     [
    0.36
     pól
    0.36
    POSITIVE LOGITS
    েল
    0.40
     Ranbir
    0.40
    槎
    0.39
     Joko
    0.39
    executeUpdate
    0.38
    城県
    0.38
     deportivas
    0.37
    getMaster
    0.37
     Fey
    0.37
    あらゆる
    0.37
    Activations Density 0.015%

    No Known Activations