© 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. 36858
    Prev
    Next
    INDEX
    Explanations

    eight

    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
     వా
    0.38
    惊
    0.38
    sqcup
    0.35
     Faust
    0.34
    äume
    0.34
    教会
    0.34
     فش
    0.33
     differ
    0.33
     sept
    0.32
    ipated
    0.32
    POSITIVE LOGITS
    八
    1.04
     八
    1.00
     Eight
    0.99
     eight
    0.93
    8
    0.90
    Eight
    0.89
     oito
    0.88
     acht
    0.82
     आठ
    0.81
     Eighth
    0.81
    Activations Density 0.034%

    No Known Activations