© 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. 201287
    Prev
    Next
    INDEX
    Explanations

    Puget Sound

    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
    elis
    0.42
     El
    0.39
    macd
    0.39
    chim
    0.38
    pez
    0.38
    ెక్
    0.38
    El
    0.37
     ህ
    0.37
    Mac
    0.36
    EDE
    0.36
    POSITIVE LOGITS
     Scre
    0.42
    فاوت
    0.41
     Fans
    0.39
    Heading
    0.39
     भारी
    0.38
    ہوری
    0.36
    <0x88>
    0.35
    Fans
    0.35
    URDAY
    0.35
    igation
    0.35
    Activations Density 0.000%

    No Known Activations