© 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. 129050
    Prev
    Next
    INDEX
    Explanations

    determine the following

    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
    u
    1.30
    k
    1.25
    OND
    1.16
    ay
    1.14
    RY
    1.14
    و
    1.14
    ANDE
    1.13
    ו
    1.13
    ys
    1.12
    uk
    1.11
    POSITIVE LOGITS
     to
    1.04
     It
    0.96
     निकाल
    0.93
    ת
    0.91
     hernia
    0.89
     식으로
    0.88
    のは
    0.88
     وضاحت
    0.88
     recorrer
    0.87
     पढ़ा
    0.85
    Activations Density 0.001%

    No Known Activations