© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170310
    Prev
    Next
    INDEX
    Explanations

    installed capacity

    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_20_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
    ཛ
    0.46
    Seine
    0.46
    FunctionName
    0.44
    ام
    0.43
    Improvements
    0.43
     geospatial
    0.43
     carri
    0.43
    Geolocation
    0.42
     amenity
    0.41
    Scenic
    0.41
    POSITIVE LOGITS
    și
    0.50
    ケーキ
    0.49
    Е
    0.48
     நேரம்
    0.47
    ać
    0.46
     Biology
    0.45
     различ
    0.45
     making
    0.44
    㶲
    0.44
     ऑर्डर
    0.43
    Activations Density 0.001%

    No Known Activations