© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30944
    Prev
    Next
    INDEX
    Explanations

    Great Wall sections

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Zhao
    1.34
    趙
    1.28
    Zhao
    1.25
    赵
    1.22
     赵
    1.02
     Chao
    0.85
     ZnO
    0.65
    hao
    0.62
    昭
    0.61
    Z
    0.55
    POSITIVE LOGITS
     Mut
    0.41
    くな
    0.40
    をクリック
    0.38
    اهرين
    0.38
    ∽
    0.38
     J
    0.38
    Mut
    0.38
    互
    0.38
    erent
    0.38
     suf
    0.37
    Activations Density 0.003%

    No Known Activations