© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27161
    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_10_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
    possibleTypes
    0.61
     සිදු
    0.55
    multiSelectList
    0.54
     ilus
    0.51
     childnya
    0.51
    ຯ
    0.51
     ignoreString
    0.50
     忄
    0.50
    穼
    0.50
    があります
    0.50
    POSITIVE LOGITS
    1
    0.56
    2
    0.56
    All
    0.55
     on
    0.52
     for
    0.52
    for
    0.51
    For
    0.51
     to
    0.51
    Et
    0.50
    To
    0.49
    Activations Density 0.000%

    No Known Activations