© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36932
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     %``
    0.41
    ~~~~
    0.37
    %(
    0.37
    %/
    0.36
    /~
    0.35
    opherol
    0.35
    ongen
    0.35
    $\{
    0.35
     акт
    0.35
    </code>
    0.34
    POSITIVE LOGITS
     الرابعه
    0.37
    paces
    0.37
    গুলি
    0.36
    ações
    0.36
    ても
    0.36
     dés
    0.35
    Wars
    0.35
    عات
    0.35
     ரசிக
    0.34
     acciones
    0.34
    Activations Density 0.010%

    No Known Activations