© 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. 210630
    Prev
    Next
    INDEX
    Explanations

    plan a trip

    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
     lớ
    0.49
     soit
    0.49
     தன்மை
    0.46
     запах
    0.46
     বহ
    0.46
     що
    0.46
     приро
    0.46
    that
    0.45
     }{
    0.45
    жей
    0.45
    POSITIVE LOGITS
    ف
    0.61
     for
    0.59
     scheduled
    0.52
    ج
    0.50
    Product
    0.49
    src
    0.49
    PO
    0.49
    duled
    0.49
    حول
    0.49
    ional
    0.49
    Activations Density 0.019%

    No Known Activations