© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16709
    Prev
    Next
    INDEX
    Explanations

    percentages and units

    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_40_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
     Commons
    0.42
    ラル
    0.39
    Yard
    0.38
    牺牲
    0.37
    Widget
    0.35
    Carousel
    0.35
    WHEREAS
    0.35
    妿
    0.35
     Brow
    0.35
    湫
    0.33
    POSITIVE LOGITS
     फर
    0.45
    жі
    0.39
    県
    0.38
    পত
    0.37
     certain
    0.36
     certaine
    0.36
    اصمة
    0.35
     Certain
    0.35
    輻
    0.35
    headers
    0.34
    Activations Density 0.047%

    No Known Activations