© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247399
    Prev
    Next
    INDEX
    Explanations

    external links to resources

    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_40_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
    ｃ
    0.36
    leb
    0.36
    itoneal
    0.35
     უკ
    0.35
     All
    0.35
    oden
    0.34
    蝸
    0.34
    athyroid
    0.33
    strument
    0.33
    लाम
    0.33
    POSITIVE LOGITS
    ⎡
    0.37
     излу
    0.35
    ume
    0.35
    Celula
    0.34
     কূট
    0.34
    ifelse
    0.34
    защи
    0.34
    ʚ
    0.34
     sout
    0.34
     TAN
    0.34
    Activations Density 0.000%

    No Known Activations