© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142421
    Prev
    Next
    INDEX
    Explanations

    maximum value

    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_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Crop
    0.63
    Fish
    0.60
    Encode
    0.60
    topLeft
    0.55
    Benchmarks
    0.55
    Wage
    0.55
    Bamboo
    0.55
    Req
    0.55
    Rooms
    0.54
    曆
    0.54
    POSITIVE LOGITS
     Emperor
    0.54
     comforting
    0.52
     👀
    0.52
    <0x98>
    0.51
     crossword
    0.50
     À
    0.49
     hooded
    0.49
     Woo
    0.49
     belong
    0.49
     Christian
    0.49
    Activations Density 0.000%

    No Known Activations