© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198034
    Prev
    Next
    INDEX
    Explanations

    classical disciplines and movements

    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_12_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
     পারিনি
    0.56
     ප්‍රති
    0.55
    уд
    0.54
     satisfait
    0.52
     Sempre
    0.51
    Ꮔ
    0.51
     vimos
    0.51
    K
    0.50
    OptionsMenu
    0.49
    myX
    0.49
    POSITIVE LOGITS
    f
    0.59
    h
    0.56
    [
    0.55
    ח
    0.55
    v
    0.53
    ه
    0.53
     damaged
    0.52
    অথ
    0.52
     लक्ष्मण
    0.51
    न
    0.51
    Activations Density 0.000%

    No Known Activations