© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33944
    Prev
    Next
    INDEX
    Explanations

    HTTP errors

    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_50_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
    ()<<"
    0.40
    ຫານ
    0.40
    츨
    0.38
    ointees
    0.38
    ników
    0.37
    ≪
    0.37
    urpose
    0.37
    վել
    0.36
    င်္ဂ
    0.35
    ण्याचा
    0.35
    POSITIVE LOGITS
    蛾
    0.42
     ezt
    0.40
    ussa
    0.40
    ART
    0.39
    asse
    0.39
     Master
    0.39
     masters
    0.39
    ura
    0.39
    七
    0.38
     rupt
    0.38
    Activations Density 0.003%

    No Known Activations