© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26966
    Prev
    Next
    INDEX
    Explanations

    HTML tags, attributes, and code structure

    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_10_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
    U
    0.56
     d
    0.54
    င်
    0.51
     s
    0.50
     to
    0.50
    1
    0.49
    Container
    0.48
    toothpaste
    0.46
     सवालों
    0.46
     a
    0.45
    POSITIVE LOGITS
    त
    0.48
    เบียน
    0.43
    이었
    0.42
    ה
    0.40
    т
    0.39
    י
    0.39
     être
    0.39
     begged
    0.38
    ®.
    0.38
    ท
    0.38
    Activations Density 0.007%

    No Known Activations