© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78215
    Prev
    Next
    INDEX
    Explanations

    Designing

    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_0_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
     is
    1.84
    ↵↵
    1.49
    8
    1.49
     {
    1.42
     a
    1.34
    ;
    1.30
    ٨
    1.30
    4
    1.27
    (
    1.23
    </strong>
    1.22
    POSITIVE LOGITS
    मधील
    1.59
    it
    1.55
    मधून
    1.48
    ل
    1.42
    л
    1.37
    yn
    1.34
    یت
    1.33
    z
    1.29
    সহ
    1.28
    िन
    1.27
    Activations Density 0.001%

    No Known Activations