© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 987
    Prev
    Next
    INDEX
    Explanations

    gradle configuration files

    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_39_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
     climatic
    0.39
    neys
    0.37
    Credit
    0.37
    샬
    0.37
     रंग
    0.36
     Shale
    0.36
    <0xB4>
    0.36
     Shr
    0.36
    パーツ
    0.36
    Staff
    0.36
    POSITIVE LOGITS
     arrayOf
    0.41
    습니다
    0.39
    उद्योग
    0.36
    وە
    0.36
    userManager
    0.36
    镟
    0.36
     explicitly
    0.35
     proguardFiles
    0.35
     எச்ச
    0.35
    uddho
    0.34
    Activations Density 0.003%

    No Known Activations