© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217847
    Prev
    Next
    INDEX
    Explanations

    original paper/poster/email

    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_31_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
    ____________
    0.38
     सचिवालय
    0.38
    ewhere
    0.37
    remainder
    0.36
    
    0.36
    ________
    0.35
    sust
    0.35
    documentation
    0.35
    \}}
    0.35
     péld
    0.35
    POSITIVE LOGITS
     boroughs
    0.40
     hydraulic
    0.40
    催
    0.38
     해
    0.38
     potřeb
    0.37
     EDA
    0.37
     ク
    0.37
    viously
    0.37
     acrylic
    0.36
     சே
    0.36
    Activations Density 0.001%

    No Known Activations