© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104981
    Prev
    Next
    INDEX
    Explanations

    issue tracking

    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_44_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
    谿
    0.39
     sucesivamente
    0.36
     Hình
    0.35
     marché
    0.35
    Ẳ
    0.35
    শ্যক
    0.35
     parenchyma
    0.34
    ඒ
    0.34
    setObjectName
    0.34
    ুটি
    0.34
    POSITIVE LOGITS
     ডাক্তার
    0.38
    Fighting
    0.38
     gang
    0.37
     inducted
    0.37
    碇
    0.36
    Cultural
    0.35
     doctor
    0.35
     डॉक्ट
    0.35
     культур
    0.35
    Strat
    0.34
    Activations Density 0.001%

    No Known Activations