© 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. 36797
    Prev
    Next
    INDEX
    Explanations

    researcher or organizational unit

    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
    ’
    0.88
    (
    0.88
     of
    0.85
     (
    0.82
    "
    0.73
    ized
    0.72
    \"
    0.70
    -
    0.68
     as
    0.66
    CAN
    0.66
    POSITIVE LOGITS
    ма
    0.84
    ان
    0.78
    يث
    0.78
    abhavo
    0.77
    филлер
    0.76
    ها
    0.75
    ０
    0.75
    lendi
    0.72
    дят
    0.71
    يار
    0.70
    Activations Density 0.013%

    No Known Activations