© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5275
    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
    Not in Any Lists

    No Comments

    Negative Logits
     গৃহ
    0.36
     bals
    0.36
    ंती
    0.36
     ત
    0.35
    
    0.34
    வியல்
    0.34
    馔
    0.34
     बाजू
    0.33
    墨
    0.32
     geni
    0.32
    POSITIVE LOGITS
     contract
    0.84
     Contract
    0.73
    Contract
    0.72
    contract
    0.70
     kontrakt
    0.68
    契約
    0.67
     계약
    0.66
     contracted
    0.65
     contracting
    0.65
    CONTRACT
    0.65
    Activations Density 0.056%

    No Known Activations