© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199065
    Prev
    Next
    INDEX
    Explanations

    foreign language actions

    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_12_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
     pię
    0.54
     ve
    0.49
     sa
    0.49
    popupIsOpen
    0.48
    ız
    0.47
     powers
    0.46
    */
    0.46
     sampai
    0.46
    .*
    0.46
     时间
    0.45
    POSITIVE LOGITS
    عد
    0.49
    らは
    0.46
     університету
    0.45
    ح
    0.44
    र्स
    0.44
    Ꮄ
    0.43
    И
    0.43
    Мо
    0.43
    и
    0.42
    رح
    0.42
    Activations Density 0.000%

    No Known Activations