© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197213
    Prev
    Next
    INDEX
    Explanations

    kids

    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_15_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
    разде
    0.54
    ذج
    0.52
    ﾘ
    0.51
    鍒
    0.51
     來
    0.50
     ندرس
    0.50
    ларын
    0.50
    釐
    0.49
     pptn
    0.49
     duplic
    0.49
    POSITIVE LOGITS
     $\
    0.66
    Après
    0.63
    به
    0.63
    entiary
    0.57
    è
    0.57
    ên
    0.57
    ه
    0.57
     having
    0.57
    èbre
    0.57
    ona
    0.56
    Activations Density 0.002%

    No Known Activations