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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26124
    Prev
    Next
    INDEX
    Explanations

    provide support

    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_10_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
     แต่
    0.69
     =>
    0.60
     Hearst
    0.60
    য
    0.59
     sampai
    0.59
     {}\
    0.57
     kV
    0.57
     (
    0.56
     Czy
    0.56
    ▶
    0.55
    POSITIVE LOGITS
    ون
    0.66
    ized
    0.66
    ρα
    0.61
    кам
    0.59
    horizontal
    0.58
    lama
    0.58
    menus
    0.58
    gee
    0.57
     городского
    0.57
    ruh
    0.57
    Activations Density 0.014%

    No Known Activations