© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84787
    Prev
    Next
    INDEX
    Explanations

    probation period

    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_0_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
    v
    1.92
    j
    1.63
    p
    1.62
    to
    1.54
    ooo
    1.42
    u
    1.39
    m
    1.38
    w
    1.38
    1.35
    م
    1.30
    POSITIVE LOGITS
    か
    1.57
    ار
    1.50
    पणे
    1.40
    の色
    1.31
    ically
    1.29
    的天
    1.27
    ভাবে
    1.20
    と考え
    1.20
    ها
    1.19
    的产品
    1.16
    Activations Density 0.000%

    No Known Activations