© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164745
    Prev
    Next
    INDEX
    Explanations

    Bruce Willis, Mel Gibson, Eddie Murphy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     Oregon
    0.56
    нд
    0.52
     Fe
    0.51
     ).
    0.51
     Baltic
    0.50
     Xian
    0.49
     Fuji
    0.47
     .
    0.47
     Fuj
    0.47
    Oregon
    0.46
    POSITIVE LOGITS
     numberOfRows
    0.55
    SOD
    0.54
    городе
    0.53
     duas
    0.52
     aussi
    0.52
     melodies
    0.51
     rahul
    0.51
     દિવસે
    0.50
     seulement
    0.50
     dní
    0.49
    Activations Density 0.000%

    No Known Activations