© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15304
    Prev
    Next
    INDEX
    Explanations

    packaging and weight

    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_13_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
    AD
    0.52
    وا
    0.50
    Media
    0.50
    Mosaic
    0.48
    Oste
    0.48
    Y
    0.48
    Instrument
    0.48
    Marine
    0.47
    MAT
    0.46
    ONES
    0.46
    POSITIVE LOGITS
    yanka
    0.48
    anbul
    0.48
     unites
    0.47
     packaging
    0.46
    aima
    0.46
    anuts
    0.45
     Savaşı
    0.45
     упаков
    0.45
    ẵ
    0.45
     packaged
    0.44
    Activations Density 0.022%

    No Known Activations