© 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. 23893
    Prev
    Next
    INDEX
    Explanations

    gelato

    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
    Negative Logits
     dgn
    0.57
     Abuse
    0.56
    षभ
    0.54
    ንሽ
    0.54
    ด์
    0.54
    ისი
    0.54
    優惠
    0.53
    ißler
    0.53
     வழங்கு
    0.52
    ح
    0.52
    POSITIVE LOGITS
    t
    0.78
    ни
    0.59
    не
    0.57
     не
    0.57
    n
    0.57
     Т
    0.52
     poorly
    0.51
     заро
    0.51
    ன்
    0.49
    ان
    0.49
    Activations Density 0.000%

    No Known Activations