© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89441
    Prev
    Next
    INDEX
    Explanations

    and much more!

    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_3_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
    ية
    1.34
    ك
    1.27
    不
    0.98
    国
    0.94
    ።
    0.94
    ير
    0.91
    ני
    0.89
    们
    0.89
    法规
    0.83
    ۔
    0.83
    POSITIVE LOGITS
    an
    0.91
    ar
    0.71
    plikasi
    0.66
     Caedwalla
    0.64
    esthetics
    0.63
    л
    0.61
    ..,
    0.61
     lalu
    0.60
    arbe
    0.60
    spers
    0.60
    Activations Density 0.005%

    No Known Activations