© 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. 207213
    Prev
    Next
    INDEX
    Explanations

    foil stamping, hats, seals, oil

    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
    st
    0.93
    re
    0.80
    з
    0.73
    ert
    0.72
    il
    0.71
     كه
    0.71
     At
    0.70
    ↵↵
    0.67
    S
    0.65
    ra
    0.65
    POSITIVE LOGITS
    0
    0.88
     invoicing
    0.84
     paparazzi
    0.82
     taxation
    0.80
     panning
    0.80
     marching
    0.78
     attorney
    0.77
     vam
    0.77
    ੇ
    0.76
     taxing
    0.75
    Activations Density 0.000%

    No Known Activations