© 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. 217509
    Prev
    Next
    INDEX
    Explanations

    say "~"

    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
    Negative Logits
    riz
    0.48
     $-
    0.46
    $-
    0.44
    niejs
    0.41
    diox
    0.40
    ্দি
    0.40
     Vlad
    0.40
    ха
    0.39
    buck
    0.39
    `-
    0.39
    POSITIVE LOGITS
     marihuana
    0.40
     arche
    0.36
     Arithmetic
    0.36
    тельному
    0.36
    EMENT
    0.35
     OIL
    0.34
     архе
    0.34
     इंजीनियरिंग
    0.34
     bargain
    0.34
     searchValue
    0.34
    Activations Density 0.001%

    No Known Activations