© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109316
    Prev
    Next
    INDEX
    Explanations

    rare words, names, or endings

    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_1_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
    '
    1.34
    ’
    1.24
    The
    1.16
    ע
    1.01
    １
    1.00
    ۰
    1.00
    ani
    0.96
    ل
    0.94
    ”
    0.94
    ）
    0.93
    POSITIVE LOGITS
    م
    1.21
    نا
    1.11
    на
    1.03
    ня
    1.03
    r
    1.02
    ui
    1.02
    नंतर
    1.01
    ни
    0.99
    是从
    0.98
    ain
    0.93
    Activations Density 0.000%

    No Known Activations