© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116132
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     करा
    0.38
    مند
    0.38
     විශ්
    0.36
    Commands
    0.36
     dakkh
    0.36
     They
    0.35
     кушымта
    0.35
    ộ
    0.35
     қили
    0.35
    comand
    0.35
    POSITIVE LOGITS
    殺人
    0.40
    দ্য
    0.38
     axe
    0.38
     tread
    0.37
    อาจ
    0.37
     Killed
    0.36
     হত্যাকাণ্ড
    0.36
     Tweed
    0.36
     ול
    0.35
     Blazers
    0.35
    Activations Density 0.000%

    No Known Activations