© 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. 10044
    Prev
    Next
    INDEX
    Explanations

    Current Status

    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
     binary
    0.51
     was
    0.49
     BTU
    0.48
     DBE
    0.48
    我
    0.47
     an
    0.46
     allege
    0.45
     arou
    0.44
     or
    0.44
     це
    0.44
    POSITIVE LOGITS
    '।
    0.49
    สินค้า
    0.48
     grandparents
    0.48
     क्रम
    0.47
    "।
    0.47
    善
    0.47
     क्रॉप
    0.47
     टाइप
    0.46
     grandpa
    0.45
     mercanc
    0.45
    Activations Density 0.001%

    No Known Activations