© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47045
    Prev
    Next
    INDEX
    Explanations

    sorting, organizing, classifying

    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_13_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
    {
    0.51
    (
    0.48
    /
    0.46
    t
    0.46
     (
    0.43
    si
    0.40
     or
    0.40
     le
    0.40
    )]
    0.39
    %
    0.38
    POSITIVE LOGITS
    𝚞
    0.52
     classifying
    0.52
    ᐢ
    0.52
    इसका
    0.51
     URANIUM
    0.50
     इसका
    0.50
    classify
    0.49
    ೋಗ್ಯ
    0.49
     Nucleaires
    0.48
     समास
    0.48
    Activations Density 0.068%

    No Known Activations