© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220380
    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_10_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
    دى
    0.46
    $-
    0.43
    داً
    0.43
     dov
    0.43
    </code>
    0.42
     הו
    0.42
    !-
    0.41
     وج
    0.41
    ribut
    0.40
     unlawfully
    0.40
    POSITIVE LOGITS
     embarazada
    0.54
     Rusia
    0.52
    鹕
    0.51
    ruzione
    0.50
    mi
    0.50
     Ru
    0.48
     Ruins
    0.47
     Rihanna
    0.46
     lasagna
    0.46
    òa
    0.46
    Activations Density 0.000%

    No Known Activations