© 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. 217657
    Prev
    Next
    INDEX
    Explanations

    time abbreviations

    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
    ्वी
    0.42
     hote
    0.40
     Achieve
    0.39
    鹖
    0.38
    ]<
    0.37
    fclose
    0.36
    SqlDbType
    0.36
     Conexion
    0.36
     plur
    0.35
     сложи
    0.35
    POSITIVE LOGITS
    N
    0.47
    kla
    0.45
    বা
    0.43
    rr
    0.42
     clap
    0.40
    omo
    0.39
    Clay
    0.39
     clays
    0.39
    RR
    0.39
    oma
    0.38
    Activations Density 0.011%

    No Known Activations