© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58989
    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_11_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
    嬋
    0.47
    頴
    0.45
     rapidity
    0.44
    ITIONAL
    0.43
    Visible
    0.42
    Printing
    0.42
    Tolerance
    0.42
     relativi
    0.42
    ভাবে
    0.42
    検討
    0.41
    POSITIVE LOGITS
    {$\
    0.53
    others
    0.52
    ب
    0.51
    timers
    0.50
    ulates
    0.49
    ulators
    0.47
    me
    0.47
     timbre
    0.47
    cf
    0.47
    ूठी
    0.47
    Activations Density 0.000%

    No Known Activations