© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241423
    Prev
    Next
    INDEX
    Explanations

    supply chain visibility management

    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_40_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
     ሁሉም
    0.38
     뒷
    0.38
    흥
    0.33
     Radiation
    0.33
     Supported
    0.33
     підпри
    0.33
     günlük
    0.33
    射线
    0.33
    SELECTED
    0.32
    pix
    0.32
    POSITIVE LOGITS
    িলে
    0.36
    Ղ
    0.35
    佗
    0.35
     rarity
    0.34
     للق
    0.34
     Weing
    0.34
     ata
    0.33
     warm
    0.33
    rások
    0.33
    Д
    0.33
    Activations Density 0.002%

    No Known Activations