© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129501
    Prev
    Next
    INDEX
    Explanations

    sharpen, sharjah, sharps

    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_1_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
    ر
    1.89
    د
    1.63
    ন
    1.37
    تين
    1.30
    تون
    1.30
    ться
    1.27
    ه
    1.19
    رخ
    1.16
    تنا
    1.16
    تل
    1.13
    POSITIVE LOGITS
    deki
    1.23
    是
    1.10
    는
    1.09
    ra
    1.03
    에
    1.01
    de
    0.97
    나
    0.96
    ,
    0.95
    は
    0.90
     is
    0.89
    Activations Density 0.000%

    No Known Activations