© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203433
    Prev
    Next
    INDEX
    Explanations

    makemake

    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_6_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
    '
    1.16
    Α
    1.10
     for
    1.09
    for
    0.99
    時に
    0.95
    Е
    0.90
    ᱒
    0.89
    $('#
    0.89
    ᱖
    0.88
    them
    0.88
    POSITIVE LOGITS
    ;
    1.34
     to
    1.17
    ,
    1.14
     is
    1.09
    в
    1.03
    ль
    1.02
     ELISA
    1.00
     integrate
    0.99
     oth
    0.98
     emberek
    0.98
    Activations Density 0.004%

    No Known Activations