© 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. 135630
    Prev
    Next
    INDEX
    Explanations

    obra maestra

    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
    K
    1.31
    ᱑
    1.20
    Q
    1.19
    Z
    1.13
    H
    1.08
    U
    1.08
    ᱖
    1.07
    V
    1.05
    ᱒
    1.05
    ᱗
    1.05
    POSITIVE LOGITS
    in
    1.63
    s
    1.57
    ير
    1.28
    ים
    1.13
    ات
    0.98
    يث
    0.98
    ف
    0.97
    uje
    0.94
     في
    0.92
     C
    0.91
    Activations Density 0.000%

    No Known Activations