© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 198485
    Prev
    Next
    INDEX
    Explanations

    Tutorial

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     ఎలా
    0.42
     Array
    0.40
     भया
    0.39
    Sites
    0.39
    叧
    0.38
     "*");
    0.38
     আর
    0.37
    Psalm
    0.37
     Webs
    0.37
    Legisl
    0.37
    POSITIVE LOGITS
     point
    0.46
     punto
    0.42
     Monica
    0.40
    点が
    0.39
    点
    0.39
    stol
    0.39
    ponden
    0.38
     POINT
    0.38
     validate
    0.37
    點
    0.36
    Activations Density 0.001%

    No Known Activations