© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176859
    Prev
    Next
    INDEX
    Explanations

    comprising a part or function

    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_20_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
    电子邮件
    0.46
     அது
    0.45
    Recipes
    0.42
     কেজি
    0.42
     appris
    0.41
    क्रम
    0.41
     נישט
    0.41
    <unused1062>
    0.41
     Comercial
    0.40
    жба
    0.40
    POSITIVE LOGITS
     AR
    0.46
     elements
    0.44
    icies
    0.44
     such
    0.42
    inees
    0.42
     tackle
    0.42
     coalesce
    0.42
     cy
    0.41
     kte
    0.41
     features
    0.40
    Activations Density 0.000%

    No Known Activations