© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62429
    Prev
    Next
    INDEX
    Explanations

    RTX GPUs, performance, blocker

    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_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
    a
    0.34
    t
    0.33
    f
    0.30
    canoe
    0.30
    *
    0.29
    {
    0.29
    shoring
    0.28
    c
    0.28
     Daphne
    0.27
    sher
    0.27
    POSITIVE LOGITS
    ни
    0.34
     हमेशा
    0.34
     همیشه
    0.32
    ība
    0.32
     कीमतें
    0.32
    ु
    0.31
    ナトリウム
    0.31
     Пока
    0.31
    ུ
    0.30
    нические
    0.30
    Activations Density 0.122%

    No Known Activations