© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207128
    Prev
    Next
    INDEX
    Explanations

    image file extensions

    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_10_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
     be
    0.70
    ATION
    0.62
     emergencies
    0.61
    ics
    0.61
     ASSOCIATION
    0.59
    ER
    0.58
    痙
    0.58
    ى
    0.58
    ation
    0.57
     pancreas
    0.57
    POSITIVE LOGITS
    a
    1.08
    s
    0.78
    the
    0.77
    killed
    0.71
     kutoka
    0.69
    in
    0.67
    ра
    0.66
    ah
    0.66
    ia
    0.65
    filling
    0.65
    Activations Density 0.000%

    No Known Activations