© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206493
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     উর্দু
    0.40
    減少
    0.40
    适应
    0.38
    卋
    0.38
     simultaneous
    0.37
     التالية
    0.36
    篌
    0.36
    改變
    0.36
     নিয়ে
    0.35
    㬶
    0.35
    POSITIVE LOGITS
    ভিল
    0.39
    볍
    0.39
    grams
    0.36
    верка
    0.36
    水平
    0.35
    rizes
    0.35
    යක
    0.35
     Monsters
    0.35
    innaker
    0.35
     horoscope
    0.34
    Activations Density 0.000%

    No Known Activations