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

    Neuronpedia

    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. 9685
    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
     ABI
    0.26
    Á
    0.26
     provided
    0.25
    Ú
    0.25
    API
    0.23
     nickel
    0.23
    CL
    0.23
    CRY
    0.23
    DB
    0.22
    AW
    0.22
    POSITIVE LOGITS
    こう
    0.26
    ).$$
    0.26
     डिजी
    0.25
     ডিজি
    0.25
    -'].
    0.25
    ))$.
    0.24
    园
    0.23
    organisation
    0.23
    ^{-/-}$
    0.22
    が決
    0.22
    Activations Density 0.002%

    No Known Activations