© 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. 87809
    Prev
    Next
    INDEX
    Explanations

    ide, js, Sisters

    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
    {
    0.79
    as
    0.76
    ス
    0.75
    it
    0.74
    s
    0.73
    স
    0.71
     öğrenciler
    0.70
    ی
    0.70
    ዷ
    0.68
    であった
    0.66
    POSITIVE LOGITS
     of
    0.76
    la
    0.61
    los
    0.60
    ia
    0.59
    ling
    0.59
    ü
    0.59
     २
    0.54
     on
    0.53
    ao
    0.52
    ुर
    0.52
    Activations Density 0.000%

    No Known Activations