© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226451
    Prev
    Next
    INDEX
    Explanations

    expressions of help or gratitude

    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_6_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
    ur
    1.62
    ad
    1.61
    ing
    1.40
    h
    1.37
    ed
    1.30
    y
    1.30
    v
    1.29
     on
    1.27
    us
    1.27
    ere
    1.27
    POSITIVE LOGITS
    ذي
    1.05
    كه
    0.96
    ໃນ
    0.94
    וס
    0.93
    '
    0.93
     σε
    0.89
    нии
    0.89
     nisam
    0.88
    ち
    0.88
     trecut
    0.86
    Activations Density 0.001%

    No Known Activations