© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43607
    Prev
    Next
    INDEX
    Explanations

    override file include

    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
    دو
    0.57
     evi
    0.57
    {
    0.55
     шесть
    0.53
     хотим
    0.53
    as
    0.52
    os
    0.51
    es
    0.50
     Кор
    0.49
    {}'.
    0.49
    POSITIVE LOGITS
     apparatus
    0.66
    ני
    0.62
    کنندگان
    0.55
    erald
    0.54
     fray
    0.53
     শুনানি
    0.53
    ärg
    0.52
     arba
    0.52
    landish
    0.52
    丁寧に
    0.52
    Activations Density 0.001%

    No Known Activations