© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209753
    Prev
    Next
    INDEX
    Explanations

    retrospective

    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_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     be
    1.27
    ك
    1.23
    K
    1.11
    ется
    1.02
    いますが
    1.02
    Wie
    0.98
     बढ़ावा
    0.96
    b
    0.95
    H
    0.94
    be
    0.93
    POSITIVE LOGITS
    ী
    1.48
    ار
    1.44
    ات
    1.40
    ים
    1.36
    is
    1.32
    ות
    1.30
    um
    1.26
    রা
    1.22
     zebrafish
    1.19
    od
    1.16
    Activations Density 0.001%

    No Known Activations