© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135473
    Prev
    Next
    INDEX
    Explanations

    right place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    ствующих
    0.39
    邑
    0.38
     ಇಲ್ಲಿ
    0.38
     Acá
    0.35
    恵
    0.35
     supplied
    0.35
    acyjnych
    0.35
     Nye
    0.35
     बेटियों
    0.35
    ถุน
    0.35
    POSITIVE LOGITS
     siv
    0.38
    谈
    0.38
     wizard
    0.37
    竿
    0.37
    整个
    0.36
    整個
    0.36
    慢性
    0.36
     ander
    0.35
    全身
    0.35
    ވަ
    0.35
    Activations Density 0.001%

    No Known Activations