© 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. 50409
    Prev
    Next
    INDEX
    Explanations

    Chinese provinces

    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
    u
    0.94
    एम
    0.81
     घेतली
    0.72
    in
    0.71
    다
    0.71
    Metro
    0.68
     annoyance
    0.68
    M
    0.68
    ペン
    0.67
    다면
    0.67
    POSITIVE LOGITS
    :
    0.68
    ges
    0.67
     Deutschen
    0.66
    {
    0.66
    ues
    0.65
    unez
    0.64
    0
    0.63
    ش
    0.63
    ص
    0.63
    ваць
    0.63
    Activations Density 0.001%

    No Known Activations