© 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. 41105
    Prev
    Next
    INDEX
    Explanations

    quality assurance

    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
    Negative Logits
    缺少
    0.51
     потрібно
    0.49
    Lack
    0.48
     authorized
    0.44
    చ్చు
    0.44
    哋
    0.44
    iad
    0.43
    이라고
    0.43
    󠁢
    0.43
     Tencent
    0.43
    POSITIVE LOGITS
     iconos
    0.48
     dissol
    0.48
     సాహిత్య
    0.46
     granules
    0.45
    м
    0.45
     Blut
    0.45
     Quran
    0.44
     Dados
    0.44
     Dauer
    0.44
     Landmarks
    0.44
    Activations Density 0.007%

    No Known Activations