© 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. 62382
    Prev
    Next
    INDEX
    Explanations

    clojure

    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_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
    :”
    0.22
    :“
    0.19
    :",
    0.18
    D
    0.18
    :")
    0.18
    :"
    0.17
    :**
    0.17
    an
    0.17
    Cl
    0.17
    P
    0.17
    POSITIVE LOGITS
     mesmer
    0.17
     sami
    0.16
     меня
    0.16
    amburger
    0.15
     сами
    0.15
     фокуси
    0.15
     sensational
    0.15
     asymptotically
    0.15
    моби
    0.15
     siempre
    0.14
    Activations Density 0.003%

    No Known Activations