© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 168037
    Prev
    Next
    INDEX
    Explanations

    section headings and lists

    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_31_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
    కంగా
    0.37
    usus
    0.37
     tức
    0.37
     الكت
    0.37
     फाइन
    0.36
    icional
    0.35
     कारा
    0.35
    LogRow
    0.35
    环
    0.35
    ítulo
    0.34
    POSITIVE LOGITS
    තර
    0.42
     sixteen
    0.38
     Transitions
    0.38
     recreated
    0.38
    hygine
    0.38
     deterministic
    0.37
    ReactNative
    0.37
     setActive
    0.37
    ក្ខ
    0.37
     discount
    0.36
    Activations Density 0.000%

    No Known Activations