© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200550
    Prev
    Next
    INDEX
    Explanations

    react, data binding, programming model

    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_12_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
    an
    0.55
    ical
    0.54
     semplice
    0.50
     These
    0.49
    ets
    0.49
    ではありません
    0.49
    ע
    0.47
     ACO
    0.46
    ACO
    0.46
    Santa
    0.46
    POSITIVE LOGITS
    㡷
    0.53
    تحان
    0.51
    த்ரே
    0.50
    何况
    0.50
     बढ़त
    0.50
     पैमाने
    0.50
     анализа
    0.49
    σης
    0.49
    रांत
    0.49
    তনে
    0.49
    Activations Density 0.000%

    No Known Activations