© 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. 179729
    Prev
    Next
    INDEX
    Explanations

    Grat

    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
    checkFor
    0.42
    omio
    0.39
     canary
    0.39
     Gerrit
    0.37
    闻
    0.37
    jeva
    0.37
     матери
    0.37
    urni
    0.37
    教
    0.37
     unity
    0.36
    POSITIVE LOGITS
    itudes
    0.78
    ITUDE
    0.76
    itude
    0.72
    itud
    0.54
    itudine
    0.52
     Tud
    0.49
     attitudes
    0.48
     Attitudes
    0.48
     Dud
    0.45
     Attitude
    0.45
    Activations Density 0.000%

    No Known Activations