© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143738
    Prev
    Next
    INDEX
    Explanations

    Maps and addresses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     التس
    0.39
    picking
    0.39
    ραγ
    0.37
    資本
    0.37
    poetry
    0.35
     независи
    0.34
    ឍ
    0.33
    าก
    0.33
     Cum
    0.33
    செ
    0.33
    POSITIVE LOGITS
     OS
    1.88
     Ordinance
    1.58
     Ordnance
    1.50
    OS
    1.45
     ordinance
    1.45
     ordnance
    1.42
     os
    1.27
     Os
    1.11
     ос
    1.08
     Ordn
    1.06
    Activations Density 0.001%

    No Known Activations