© 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. 200282
    Prev
    Next
    INDEX
    Explanations

    guided tour

    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
    '
    1.23
    <0x80>
    1.19
    די
    1.15
    ו
    1.09
    บ
    1.02
    я
    1.01
    ק
    1.00
    א
    0.99
    ย
    0.97
    ="
    0.96
    POSITIVE LOGITS
     Ичиго
    1.12
    وم
    1.11
    inees
    0.91
     in
    0.88
    在
    0.88
    hões
    0.86
    ంథ
    0.86
    lg
    0.86
    mány
    0.86
     appendages
    0.85
    Activations Density 0.000%

    No Known Activations