© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27084
    Prev
    Next
    INDEX
    Explanations

    parenthetical explanations

    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
     on
    0.59
    I
    0.55
    我们
    0.54
    j
    0.54
     is
    0.53
    យើង
    0.50
    เรา
    0.48
    Vý
    0.47
    "
    0.46
     appré
    0.45
    POSITIVE LOGITS
    म
    0.59
     Chichester
    0.52
    <0x80>
    0.49
     Gresham
    0.49
     Karnataka
    0.46
     QLabel
    0.46
    मधील
    0.45
     Bundestag
    0.45
     (
    0.44
     cmap
    0.43
    Activations Density 0.048%

    No Known Activations