© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40238
    Prev
    Next
    INDEX
    Explanations

    bounce back

    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_11_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
    ா
    0.34
    க்கிர
    0.34
    мережа
    0.33
     кі
    0.31
    FRINGEMENT
    0.30
     ಕು
    0.29
     Lions
    0.28
     Doh
    0.28
     Kyi
    0.28
    }{
    0.27
    POSITIVE LOGITS
    v
    0.34
    vet
    0.28
    fs
    0.27
    hav
    0.26
    vis
    0.25
    рите
    0.25
    i
    0.25
    pe
    0.25
    vare
    0.25
    ver
    0.25
    Activations Density 0.005%

    No Known Activations