© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48399
    Prev
    Next
    INDEX
    Explanations

    say "."

    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_55_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
     उद्योगों
    0.40
    даг
    0.40
     Mainly
    0.40
    器件
    0.39
     የግ
    0.39
     Businesses
    0.38
     フレーム
    0.38
    跄
    0.38
     दोग
    0.37
    
    0.37
    POSITIVE LOGITS
    athers
    0.43
    éssel
    0.38
    ურ
    0.36
    conf
    0.36
    hammer
    0.36
    ພ
    0.36
     .
    0.36
    customer
    0.36
    avac
    0.36
     evident
    0.35
    Activations Density 0.001%

    No Known Activations