© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198232
    Prev
    Next
    INDEX
    Explanations

    Momentum

    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
     rating
    0.39
     إيران
    0.39
    radian
    0.39
     Irwin
    0.38
     radian
    0.38
    炤
    0.37
     الدا
    0.37
    ives
    0.37
     ಮಟ್ಟ
    0.37
     alent
    0.37
    POSITIVE LOGITS
     iniz
    0.45
    nitz
    0.38
    Edition
    0.37
    叠
    0.35
    ক্ষার
    0.35
     Edition
    0.34
    Ui
    0.33
    STA
    0.33
    ভূমি
    0.33
     monies
    0.33
    Activations Density 0.001%

    No Known Activations