© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 200050
    Prev
    Next
    INDEX
    Explanations

    multilingual texts or phrases

    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_9_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
     كال
    0.50
     ne
    0.50
    9
    0.48
     الل
    0.47
     سلامت
    0.47
     ك
    0.45
     November
    0.44
    ؟
    0.44
     و
    0.44
     beant
    0.43
    POSITIVE LOGITS
     paredes
    0.57
     runways
    0.57
     railways
    0.56
     Aś
    0.55
     triads
    0.52
     polytopes
    0.52
     dominions
    0.52
     kurta
    0.52
    INION
    0.51
     booms
    0.51
    Activations Density 0.000%

    No Known Activations