© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76841
    Prev
    Next
    INDEX
    Explanations

    accessible

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     handbook
    0.41
    Handbook
    0.38
    న్నో
    0.37
    acat
    0.37
    গম
    0.37
    ሠራ
    0.36
    acı
    0.35
    ">%
    0.35
    ctomy
    0.35
    genza
    0.35
    POSITIVE LOGITS
    ус
    0.33
    রাতে
    0.33
     ferme
    0.33
    NSArray
    0.32
    കര
    0.32
    是的
    0.32
     Bank
    0.31
     Cas
    0.31
     ）
    0.31
    ］
    0.31
    Activations Density 0.011%

    No Known Activations