© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121595
    Prev
    Next
    INDEX
    Explanations

    describing academic or technical content

    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_27_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
    чами
    0.37
    сте
    0.34
     作品
    0.34
     反
    0.34
    广
    0.34
    ole
    0.33
    র্ম
    0.33
    umbered
    0.33
     建
    0.33
     という
    0.33
    POSITIVE LOGITS
    笑道
    0.38
     laughs
    0.35
     assicur
    0.35
     चाहेंगे
    0.34
     postureProxy
    0.34
     दावा
    0.33
     capire
    0.33
     assures
    0.33
    Cela
    0.33
    <th>
    0.33
    Activations Density 0.021%

    No Known Activations