© 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. 123785
    Prev
    Next
    INDEX
    Explanations

    on purchases, on exchange

    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
    ى
    1.25
    не
    0.77
    но
    0.75
    า
    0.75
    ಾ
    0.74
    וש
    0.65
     COO
    0.64
    ят
    0.61
    ing
    0.60
    iy
    0.59
    POSITIVE LOGITS
    in
    1.12
     to
    0.95
    न
    0.93
    OV
    0.83
    I
    0.79
    Color
    0.77
    ul
    0.74
    COLORS
    0.74
    C
    0.73
    ET
    0.71
    Activations Density 0.000%

    No Known Activations