© 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. 13447
    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
    ipak
    0.41
    発
    0.37
     bhavati
    0.35
    indole
    0.34
    幢
    0.33
     particip
    0.33
    atica
    0.32
     tagName
    0.32
     poté
    0.31
     статус
    0.31
    POSITIVE LOGITS
     Produktions
    0.37
    дил
    0.35
    zył
    0.34
    Run
    0.33
    Filters
    0.33
    ਣਾ
    0.33
     set
    0.33
     Sammlung
    0.32
    uzo
    0.32
    ,+\
    0.32
    Activations Density 0.000%

    No Known Activations