© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10229
    Prev
    Next
    INDEX
    Explanations

    cloud sdk and auth commands

    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
     Phần
    0.58
     還
    0.55
     transformar
    0.52
     聞い
    0.52
     ETF
    0.50
     ",")
    0.49
     Dwarf
    0.49
     ១
    0.49
     subray
    0.49
     Column
    0.48
    POSITIVE LOGITS
    ת
    0.57
    В
    0.54
    aç
    0.54
    ned
    0.53
    اض
    0.53
    {
    0.53
    ت
    0.52
    ס
    0.50
    ed
    0.49
     jed
    0.49
    Activations Density 0.002%

    No Known Activations