© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24695
    Prev
    Next
    INDEX
    Explanations

    minefield or rollicking

    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
    t
    0.67
    л
    0.64
    er
    0.61
    ar
    0.60
     від
    0.60
    rer
    0.59
    al
    0.56
    ori
    0.55
    :
    0.55
    ra
    0.54
    POSITIVE LOGITS
    Typography
    0.57
    '
    0.52
    昌
    0.49
    ષા
    0.48
    ưới
    0.47
    聚
    0.47
    ジュール
    0.47
     þei
    0.47
    甠
    0.46
     Spaces
    0.46
    Activations Density 0.000%

    No Known Activations