© 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. 129116
    Prev
    Next
    INDEX
    Explanations

    danger

    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
    1.38
    0
    1.27
     that
    1.23
    that
    1.23
    ک
    1.23
    ص
    1.08
    си
    1.07
    of
    1.05
    AG
    1.05
    تی
    1.00
    POSITIVE LOGITS
     C
    0.91
     L
    0.89
     HAS
    0.89
     I
    0.88
    什么
    0.88
    可谓
    0.87
     S
    0.86
     Z
    0.83
     V
    0.81
     ha
    0.80
    Activations Density 0.001%

    No Known Activations