© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14712
    Prev
    Next
    INDEX
    Explanations

    background story

    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_13_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
    ر
    0.66
    ，
    0.63
     punctul
    0.59
    יי
    0.58
    ،
    0.57
     dendritic
    0.55
    器
    0.55
    队
    0.54
    ג
    0.54
    کی
    0.52
    POSITIVE LOGITS
    History
    0.62
     истории
    0.62
     histories
    0.60
    {
    0.59
    long
    0.59
     Historia
    0.59
     культуры
    0.57
     historie
    0.57
     التاريخ
    0.57
     istor
    0.55
    Activations Density 0.033%

    No Known Activations