© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238039
    Prev
    Next
    INDEX
    Explanations

    May 2nd, 4/20, Irish heritage

    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_32_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
    ഗി
    0.39
    玮
    0.37
     obiect
    0.35
     addressed
    0.35
    updates
    0.35
    瘍
    0.34
    ீன்
    0.34
    련
    0.33
     chosen
    0.33
    萱
    0.33
    POSITIVE LOGITS
    League
    0.38
    MenuList
    0.38
    Menus
    0.38
     dinast
    0.37
     seeding
    0.35
     Streak
    0.35
    nus
    0.35
     колдон
    0.35
    嬉
    0.35
     deserialize
    0.34
    Activations Density 0.001%

    No Known Activations