© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30162
    Prev
    Next
    INDEX
    Explanations

    Intel Core i series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ي
    0.87
    Core
    0.81
    ে
    0.80
    া
    0.77
    ס
    0.77
    Zeros
    0.75
    ਰ
    0.75
    i
    0.72
    ר
    0.70
    Truck
    0.69
    POSITIVE LOGITS
    í
    0.63
    soever
    0.62
     this
    0.57
    աբ
    0.55
    wezig
    0.54
    ēm
    0.53
    ía
    0.53
    ian
    0.52
     much
    0.52
    ным
    0.52
    Activations Density 0.002%

    No Known Activations