© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232162
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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_32_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
     touring
    0.51
     concerts
    0.49
     circuitos
    0.46
     stagione
    0.46
     項
    0.45
     viaj
    0.42
     tour
    0.42
     шоу
    0.41
     circuit
    0.40
    Season
    0.40
    POSITIVE LOGITS
     Importing
    0.35
     transformation
    0.34
    ilebilir
    0.34
    isma
    0.34
     office
    0.34
    office
    0.34
     application
    0.34
    崁
    0.34
    íso
    0.33
    puce
    0.33
    Activations Density 0.003%

    No Known Activations