© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43021
    Prev
    Next
    INDEX
    Explanations

    trucks, bars, vehicles

    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
    ل
    0.92
    il
    0.71
     I
    0.66
     L
    0.65
     +
    0.64
     skipper
    0.64
    艨
    0.63
     ×
    0.63
     or
    0.62
     F
    0.62
    POSITIVE LOGITS
    ۔
    0.73
    ב
    0.71
    は
    0.69
    ا۔
    0.63
    MO
    0.61
    ری
    0.61
    を取得
    0.61
    くちゃ
    0.61
    сійскай
    0.61
    ЕД
    0.60
    Activations Density 0.000%

    No Known Activations