© 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. 213020
    Prev
    Next
    INDEX
    Explanations

    more or greater

    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
    ལ
    0.38
    EPO
    0.37
     ลอง
    0.36
     Und
    0.36
    ása
    0.36
    ikki
    0.36
     नाही
    0.36
    нды
    0.36
    folios
    0.35
    ani
    0.34
    POSITIVE LOGITS
     меку
    0.39
     great
    0.39
     powerful
    0.39
     робо
    0.38
     ш
    0.38
     coc
    0.38
     Livingston
    0.36
     BEING
    0.36
     jelly
    0.36
     berpeng
    0.36
    Activations Density 0.002%

    No Known Activations