© 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. 15803
    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
    analog
    0.39
    ϓ
    0.39
    を表示
    0.38
    matrices
    0.37
    sequences
    0.37
    buildings
    0.36
    fah
    0.36
    $("
    0.36
    Dichloro
    0.35
    Springer
    0.35
    POSITIVE LOGITS
     list
    0.44
     newItem
    0.42
     newcomer
    0.42
     mean
    0.39
     Engagement
    0.38
     resentment
    0.38
     NFT
    0.37
    雰
    0.37
     zero
    0.37
     intended
    0.37
    Activations Density 0.032%

    No Known Activations