© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9413
    Prev
    Next
    INDEX
    Explanations

    hemolysis, roguelike, Diablo, seed

    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_13_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
    꾿
    0.19
    Avi
    0.19
    பாய்
    0.19
     techs
    0.17
    וד
    0.17
    ूक
    0.16
    LGBT
    0.16
     sluč
    0.16
    LLDB
    0.16
    بو
    0.16
    POSITIVE LOGITS
    i
    0.23
     Buren
    0.20
     vende
    0.19
     валю
    0.18
     sizi
    0.17
    董事长
    0.17
     verkaufen
    0.17
     магазин
    0.17
     Patt
    0.16
    ').
    0.16
    Activations Density 0.003%

    No Known Activations