© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76090
    Prev
    Next
    INDEX
    Explanations

    over or under

    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_31_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
    órm
    0.32
     Sana
    0.31
     sana
    0.30
     Sabrina
    0.30
    ńca
    0.30
     crít
    0.30
     foraging
    0.30
    //=
    0.30
     multiple
    0.29
    刍
    0.29
    POSITIVE LOGITS
    diocese
    0.34
    蛇
    0.31
    गरी
    0.30
    搅拌
    0.30
    snake
    0.29
    aigne
    0.29
     دینی
    0.29
    天才
    0.29
    Overse
    0.29
    ⦖
    0.29
    Activations Density 0.001%

    No Known Activations