© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30136
    Prev
    Next
    INDEX
    Explanations

    seven wonders, seven churches, seven transmembrane, 7nm

    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_10_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
    ,
    0.79
    ا
    0.77
     potro
    0.75
    ści
    0.74
    ಳಿತ
    0.71
     сохра
    0.71
    mö
    0.70
     hypersurfaces
    0.70
     борь
    0.68
     anuv
    0.67
    POSITIVE LOGITS
    ای
    0.79
    Seventh
    0.74
    약
    0.73
    ود
    0.71
    در
    0.70
    ат
    0.70
    ెంట్‌
    0.69
    These
    0.69
    ють
    0.68
    ية
    0.68
    Activations Density 0.072%

    No Known Activations