© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36718
    Prev
    Next
    INDEX
    Explanations

    hide out

    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_3_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
    h
    1.00
    -
    0.77
    t
    0.69
    s
    0.66
    ่
    0.66
    ้
    0.63
    hut
    0.62
    ्य
    0.61
    ↵
    0.60
    .
    0.59
    POSITIVE LOGITS
    ifiez
    0.70
    К
    0.68
     एक्ट्रेसेस
    0.67
    го
    0.66
    toBeTruthy
    0.65
    ۵
    0.65
    ۶
    0.65
    maßen
    0.64
     dirigeants
    0.63
    အ
    0.63
    Activations Density 0.001%

    No Known Activations