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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197002
    Prev
    Next
    INDEX
    Explanations

    who has

    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_26_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
     ფუნქ
    0.45
     நு
    0.40
     სხვა
    0.38
    cooking
    0.38
     நிகழ்ச்ச
    0.38
    空格
    0.37
    ભ
    0.37
    ມີ
    0.37
    ของ
    0.37
    पदा
    0.37
    POSITIVE LOGITS
     totalité
    0.41
     wandered
    0.38
     kautta
    0.38
     wanders
    0.37
     convertir
    0.36
     enriching
    0.36
     tornou
    0.36
    Planner
    0.36
     lai
    0.36
     tanker
    0.35
    Activations Density 0.000%

    No Known Activations