© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61672
    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_59_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
    direct
    0.49
    rating
    0.49
    diagn
    0.45
     G
    0.45
    ratings
    0.45
    conference
    0.45
    culture
    0.45
    molecular
    0.44
    finance
    0.44
    farm
    0.44
    POSITIVE LOGITS
    R
    0.83
    VIEW
    0.64
     VIEW
    0.63
    T
    0.58
     view
    0.56
    D
    0.54
    L
    0.51
    View
    0.51
    W
    0.50
    CAST
    0.48
    Activations Density 0.000%

    No Known Activations