© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91933
    Prev
    Next
    INDEX
    Explanations

    boost:: interprocess asio json

    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
    Negative Logits
    i
    0.80
    ीन
    0.70
     すご
    0.61
    erent
    0.59
    pInBuffer
    0.58
     paraffin
    0.58
     pretensions
    0.57
    ி
    0.57
    iper
    0.56
    iato
    0.55
    POSITIVE LOGITS
    v
    0.87
    ش
    0.77
    কে
    0.76
    ני
    0.73
    ج
    0.68
    ল
    0.67
    ص
    0.66
    на
    0.63
    ক
    0.62
    ৬
    0.61
    Activations Density 0.000%

    No Known Activations