© 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. 135470
    Prev
    Next
    INDEX
    Explanations

    on-call duties

    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
    m
    1.60
    d
    1.56
    ;
    1.56
    t
    1.48
    z
    1.42
    k
    1.40
    st
    1.34
    g
    1.25
    w
    1.23
    il
    1.17
    POSITIVE LOGITS
    كر
    1.01
    亚
    0.91
    ُم
    0.89
    类的
    0.88
    ↵↵
    0.87
    ന്ത്ര
    0.87
    াক
    0.87
    UM
    0.86
     Çünkü
    0.86
    內
    0.86
    Activations Density 0.000%

    No Known Activations