© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34863
    Prev
    Next
    INDEX
    Explanations

    research topic

    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_11_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
     അമേ
    0.57
    скольку
    0.55
    ప్రత్యర్థి
    0.54
    📗
    0.53
    $;
    0.52
    Korea
    0.52
    ፕሮ
    0.51
    加えて
    0.50
    ເພ
    0.50
    menuid
    0.50
    POSITIVE LOGITS
     could
    0.65
    ä
    0.60
     fittings
    0.57
     were
    0.57
     was
    0.55
     doubles
    0.54
     la
    0.54
     should
    0.54
     might
    0.54
     recognizes
    0.54
    Activations Density 0.005%

    No Known Activations