© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28086
    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
    গুল
    0.35
    퍽
    0.34
    dump
    0.33
     logística
    0.33
     indexPath
    0.32
     haystack
    0.32
     nombr
    0.32
     rang
    0.32
    }+(\
    0.32
     Hepatitis
    0.32
    POSITIVE LOGITS
     local
    0.75
    本地
    0.74
     местных
    0.70
     местные
    0.67
    local
    0.66
    当地
    0.65
     स्थानीय
    0.63
     locally
    0.62
     LOCAL
    0.62
     местного
    0.62
    Activations Density 0.005%

    No Known Activations