© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34335
    Prev
    Next
    INDEX
    Explanations

    يات

    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
     Super
    0.41
     ليا
    0.39
     SMAD
    0.38
    arly
    0.37
     useCallback
    0.37
    ኹ
    0.37
    SUPER
    0.37
     الشكل
    0.37
     ഉണ്ടായി
    0.37
    슈
    0.37
    POSITIVE LOGITS
    galo
    0.42
    कर्ता
    0.37
    ++++++++
    0.36
     навер
    0.36
    𝘨
    0.36
     hairs
    0.35
    τρ
    0.35
    ゆる
    0.35
     திருச்சி
    0.35
    حياته
    0.35
    Activations Density 0.001%

    No Known Activations