© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196822
    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_9_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
    ad
    0.67
    p
    0.63
    at
    0.63
    as
    0.62
    current
    0.58
    c
    0.57
    be
    0.57
    ك
    0.56
    아
    0.56
    set
    0.55
    POSITIVE LOGITS
     double
    0.53
     composer
    0.50
     BY
    0.50
     megaphone
    0.50
     Clio
    0.50
     luz
    0.46
     footnote
    0.46
     Bahasa
    0.46
     fridge
    0.46
     soprano
    0.45
    Activations Density 0.000%

    No Known Activations