© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88702
    Prev
    Next
    INDEX
    Explanations

    engine states and components

    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_11_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
     дополни
    0.57
     psychosocial
    0.55
     програм
    0.52
     е
    0.52
    راجعه
    0.52
     zusätz
    0.52
     adicionales
    0.52
     neues
    0.51
     صحت
    0.51
     ދ
    0.51
    POSITIVE LOGITS
    ie
    0.67
    high
    0.63
    ייל
    0.63
    ze
    0.61
    feed
    0.61
    our
    0.61
    め
    0.61
    en
    0.60
    urre
    0.60
    re
    0.59
    Activations Density 0.012%

    No Known Activations