© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59400
    Prev
    Next
    INDEX
    Explanations

    Solution, Test, or Weaver prefixes

    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
     പുതിയ
    0.53
     ಹೆಸ
    0.50
    坆
    0.50
     reconst
    0.49
    还需要
    0.48
     בצ
    0.48
     olt
    0.48
     sö
    0.48
    ไหม
    0.47
     ٣
    0.47
    POSITIVE LOGITS
     carts
    0.52
    Constant
    0.52
    ла
    0.50
     constantly
    0.50
    geschwindigkeit
    0.49
    ப்பர்
    0.48
     constant
    0.48
    FG
    0.48
    BG
    0.48
    ޤ
    0.47
    Activations Density 0.009%

    No Known Activations