© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19137
    Prev
    Next
    INDEX
    Explanations

    Mikel

    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_40_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
     economists
    0.39
    entra
    0.39
     katanya
    0.39
     অর্থনীতি
    0.38
     traders
    0.37
     प्रतिस्पर्धा
    0.37
     analysts
    0.36
     የቀ
    0.36
    CommandBuffer
    0.35
    ╯
    0.35
    POSITIVE LOGITS
     সহ
    0.38
     initiator
    0.37
    іл
    0.36
    Az
    0.36
     owner
    0.35
    源
    0.34
     Aged
    0.33
     السلام
    0.33
     Important
    0.33
    Excerpt
    0.33
    Activations Density 0.003%

    No Known Activations