© 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. 24255
    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
    Not in Any Lists

    No Comments

    Negative Logits
     atlet
    0.52
    艾
    0.52
     außen
    0.52
     außerhalb
    0.51
    зів
    0.50
     aller
    0.48
    ِلِّ
    0.48
     enthalten
    0.48
    越
    0.47
     betrachtet
    0.46
    POSITIVE LOGITS
     S
    0.48
    ক্তি
    0.47
    当該
    0.47
    </strong>
    0.46
     本体
    0.45
     Gle
    0.45
     С
    0.44
     이제
    0.44
     получаем
    0.43
     زیبایی
    0.42
    Activations Density 0.000%

    No Known Activations