© 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. 78367
    Prev
    Next
    INDEX
    Explanations

    filename or codename suffix

    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
     It
    1.89
    1
    1.56
    м
    1.40
    í
    1.39
     </
    1.37
     (
    1.34
    It
    1.32
    8
    1.31
    uk
    1.30
    what
    1.29
    POSITIVE LOGITS
    ン
    1.90
    のは
    1.47
    示す
    1.47
    지
    1.43
    係る
    1.40
    টি
    1.38
    した
    1.36
    取り
    1.36
    ご連絡
    1.30
    取り組み
    1.30
    Activations Density 0.001%

    No Known Activations