© 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. 36790
    Prev
    Next
    INDEX
    Explanations

    n choose k, queens, latitude, n-gram

    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
    on
    0.70
    }\
    0.68
    но
    0.66
    ا۔
    0.65
    ا
    0.65
     cuối
    0.64
     đa
    0.59
     மேலும்
    0.58
    omore
    0.57
    xF
    0.57
    POSITIVE LOGITS
    st
    0.91
    تش
    0.61
     [
    0.60
    ל
    0.59
     Inglaterra
    0.57
    gers
    0.56
    з
    0.55
    ts
    0.55
     resistance
    0.55
    '
    0.54
    Activations Density 0.018%

    No Known Activations