© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44704
    Prev
    Next
    INDEX
    Explanations

    you choose to

    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_13_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
     روسیه
    0.72
    徫
    0.60
     সম্পদ
    0.58
    лару
    0.57
    ೋಗ್ಯ
    0.57
     평가
    0.56
     প্রজাতন্ত্র
    0.55
    ロシア
    0.54
     エネルギー
    0.54
    િક
    0.54
    POSITIVE LOGITS
    {
    0.59
    /{
    0.52
    /
    0.52
    affron
    0.50
    افيه
    0.48
    azz
    0.48
    اده
    0.48
    }{
    0.47
    Te
    0.47
    Warm
    0.46
    Activations Density 0.079%

    No Known Activations