© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193239
    Prev
    Next
    INDEX
    Explanations

    log out of websites

    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    颉
    0.41
     महत्व
    0.39
     snare
    0.39
     caroten
    0.39
     huz
    0.38
     rotational
    0.37
     chur
    0.37
     ();
    0.37
     whole
    0.36
    참
    0.36
    POSITIVE LOGITS
    ume
    0.41
    ‌های
    0.41
    ร้าย
    0.40
     authenticate
    0.39
    upta
    0.38
    authent
    0.38
    新的
    0.37
    unteer
    0.37
    authenticate
    0.37
    الصفحه
    0.36
    Activations Density 0.002%

    No Known Activations