© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151654
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_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
     liberación
    0.57
     मिथुन
    0.47
    ுகளில்
    0.47
     traduire
    0.45
    ☘
    0.45
    undering
    0.44
    履行
    0.44
    ედერ
    0.44
    ExpressCheckout
    0.44
    ிற
    0.43
    POSITIVE LOGITS
     Circum
    0.48
     t
    0.46
    ٔ
    0.45
     fry
    0.45
    נ
    0.45
     sauce
    0.44
    Chile
    0.44
    ผู้
    0.43
     ت
    0.42
     spot
    0.41
    Activations Density 0.000%

    No Known Activations