© 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. 164406
    Prev
    Next
    INDEX
    Explanations

    Chinese administrative practices

    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
    ಾರ
    0.60
    ਾਈ
    0.58
     Марафон
    0.56
    תיים
    0.55
    ля
    0.55
    糇
    0.54
     befinden
    0.52
    ية
    0.52
     conocidos
    0.51
    iería
    0.51
    POSITIVE LOGITS
    (
    0.60
     incont
    0.55
    ）；
    0.54
     The
    0.54
     an
    0.52
    （
    0.52
     Adidas
    0.51
    ing
    0.50
    your
    0.50
     pendants
    0.50
    Activations Density 0.004%

    No Known Activations