© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41272
    Prev
    Next
    INDEX
    Explanations

    SPDX-License-Identifier: MIT contract code

    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_22_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
    Outfit
    0.42
    褛
    0.41
    Aph
    0.39
    ⸩
    0.39
     кварти
    0.39
     habitudes
    0.38
     Aph
    0.38
     रिश्तेदारों
    0.38
     домов
    0.38
     dreary
    0.38
    POSITIVE LOGITS
    orn
    0.42
     juin
    0.39
     رئ
    0.38
    شم
    0.38
    signal
    0.38
    cid
    0.37
    ܣ
    0.37
    Bah
    0.37
    viles
    0.37
    broken
    0.37
    Activations Density 0.000%

    No Known Activations