© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84786
    Prev
    Next
    INDEX
    Explanations

    Thames, Lal, bacter

    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_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ר
    1.95
    т
    1.83
    ли
    1.79
    {
    1.62
     rozwiąz
    1.55
    ar
    1.54
    νε
    1.52
    رین
    1.51
    (
    1.49
    lą
    1.48
    POSITIVE LOGITS
    of
    1.18
    st
    1.05
    系
    1.02
    在他
    0.97
     eine
    0.96
    被
    0.95
    到的
    0.94
    的有
    0.92
    Millis
    0.91
    面的
    0.89
    Activations Density 0.000%

    No Known Activations