© 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. 10240
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     budget
    0.48
     Expense
    0.45
     Budget
    0.44
     бюджета
    0.43
     budgets
    0.39
     expense
    0.39
     parameter
    0.38
     köl
    0.38
     buget
    0.38
    菡
    0.38
    POSITIVE LOGITS
    present
    0.56
    Present
    0.55
     present
    0.54
     presentes
    0.49
     PRESENT
    0.49
     теку
    0.49
     présent
    0.47
     ప్రస్తు
    0.47
    Current
    0.46
    PRESENT
    0.46
    Activations Density 0.005%

    No Known Activations