© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62392
    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_11_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
    нная
    0.54
    inda
    0.51
    czka
    0.50
    arger
    0.49
    И
    0.48
    ø
    0.48
    ły
    0.48
    alami
    0.48
    सरण
    0.46
    uların
    0.46
    POSITIVE LOGITS
     Keep
    0.51
     دونك
    0.49
    清除
    0.48
     свойства
    0.46
     Medal
    0.45
     Beaux
    0.45
    牖
    0.45
     Do
    0.45
     javax
    0.44
     resumen
    0.44
    Activations Density 0.000%

    No Known Activations