© 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. 197797
    Prev
    Next
    INDEX
    Explanations

    medium

    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
    ">−</
    0.41
    ಿರುವ
    0.41
     homology
    0.39
    ಿದ್ದರೆ
    0.39
    }-{
    0.38
    ням
    0.38
    絬
    0.38
    нів
    0.37
     서울
    0.37
    𒅖
    0.36
    POSITIVE LOGITS
    conom
    0.52
    raction
    0.42
    use
    0.41
    ouses
    0.40
    one
    0.39
    ek
    0.39
    ismic
    0.39
    CO
    0.38
    cho
    0.37
    ONE
    0.36
    Activations Density 0.000%

    No Known Activations