© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139135
    Prev
    Next
    INDEX
    Explanations

    Star Wars, Jedi, walker, Empire

    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
    \
    0.61
    ﹞
    0.55
    的
    0.53
    ێر
    0.49
    น
    0.48
    peas
    0.48
     Timelapse
    0.47
    न
    0.47
     نعمل
    0.47
     dino
    0.46
    POSITIVE LOGITS
     เช
    0.52
    उंस
    0.51
     ದಿ
    0.49
     Sólo
    0.48
     controle
    0.48
     リン
    0.48
    ك
    0.48
    Ét
    0.48
     pourrait
    0.47
     Ku
    0.46
    Activations Density 0.001%

    No Known Activations