© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36527
    Prev
    Next
    INDEX
    Explanations

    pressing Enter

    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_3_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
    n
    0.93
     convoluted
    0.76
    t
    0.69
     awarding
    0.64
     impasse
    0.64
    a
    0.64
    น
    0.62
     agglut
    0.59
     grate
    0.58
     tabular
    0.57
    POSITIVE LOGITS
    1
    0.77
    5
    0.77
    2
    0.75
    Finish
    0.75
    ح
    0.72
    Controllers
    0.69
    Color
    0.68
    Day
    0.68
    ف
    0.68
    Parameters
    0.67
    Activations Density 0.002%

    No Known Activations