© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38369
    Prev
    Next
    INDEX
    Explanations

    C# `Main` method

    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_11_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
     It
    0.39
     YORK
    0.34
     Ill
    0.34
     ION
    0.33
    le
    0.33
    york
    0.33
     York
    0.32
     Ρ
    0.32
     ற
    0.32
     জানিতে
    0.32
    POSITIVE LOGITS
     heli
    0.39
    춧
    0.38
     diminu
    0.37
    사진
    0.37
     स्वर्
    0.36
     사망
    0.36
     antifungal
    0.35
    nega
    0.34
    O
    0.34
     ajud
    0.34
    Activations Density 0.003%

    No Known Activations