© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241321
    Prev
    Next
    INDEX
    Explanations

    Error Go

    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_40_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
     thinning
    0.37
    ریح
    0.37
    ಟ್ಟು
    0.37
    ulen
    0.36
    Ე
    0.36
    otest
    0.36
     dab
    0.36
    주일
    0.35
    解锁
    0.35
    贵
    0.35
    POSITIVE LOGITS
     genü
    0.40
     Land
    0.38
     প্রাসাদ
    0.37
    local
    0.36
     Sharing
    0.36
    शल
    0.35
    ститут
    0.35
     insurer
    0.35
    Pis
    0.34
     branch
    0.34
    Activations Density 0.000%

    No Known Activations