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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257686
    Prev
    Next
    INDEX
    Explanations

    previous, above, earlier

    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_22_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
    必要
    0.31
    ݨ
    0.30
    ሣ
    0.29
     ويم
    0.28
    ことを
    0.28
    ха
    0.27
    ㌔
    0.27
    设
    0.26
    イント
    0.26
     अमा
    0.26
    POSITIVE LOGITS
     Zert
    0.30
    長的
    0.30
     ((*
    0.29
    モニ
    0.28
     coppia
    0.28
     TESTS
    0.27
    IS
    0.27
     продолжа
    0.27
     fortfarande
    0.26
     joht
    0.26
    Activations Density 0.016%

    No Known Activations