© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5393
    Prev
    Next
    INDEX
    Explanations

    opening or filling up

    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_39_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
    বৃষ্টি
    0.41
     Ruk
    0.37
    DOWN
    0.35
    Off
    0.35
     muster
    0.35
     सरसों
    0.35
    根据
    0.34
    对
    0.34
     tended
    0.33
    off
    0.33
    POSITIVE LOGITS
     up
    0.70
     lên
    0.54
     upto
    0.46
     Up
    0.42
    起来
    0.41
    ึ้น
    0.39
    !="
    0.39
     ഘ
    0.38
     मेवा
    0.38
    iora
    0.38
    Activations Density 0.102%

    No Known Activations