© 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. 46047
    Prev
    Next
    INDEX
    Explanations

    on top of

    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
    pielt
    0.40
    烝
    0.39
     فرمان
    0.37
    冷凍
    0.35
     dø
    0.34
     Deputy
    0.34
     विद्यु
    0.34
    现代化
    0.34
     Bakan
    0.34
    傩
    0.33
    POSITIVE LOGITS
     حدی
    0.35
    ண்டும்
    0.33
    ####
    0.33
    ()}")
    0.32
    өн
    0.31
    ท้าย
    0.31
    }\}$.
    0.31
    未知
    0.30
     clas
    0.30
     descriptive
    0.30
    Activations Density 0.000%

    No Known Activations