© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108445
    Prev
    Next
    INDEX
    Explanations

    gale

    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_2_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
     HAS
    0.61
    ’
    0.57
     ส
    0.54
     for
    0.52
     Λ
    0.52
     NOVA
    0.52
     POV
    0.52
     CAD
    0.51
     PAG
    0.50
    il
    0.50
    POSITIVE LOGITS
    ة
    0.80
    ك
    0.77
    ية
    0.76
    {
    0.76
    ت
    0.70
    し
    0.68
    ла
    0.68
    .
    0.66
    。
    0.64
    к
    0.63
    Activations Density 0.003%

    No Known Activations