© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58810
    Prev
    Next
    INDEX
    Explanations

    duct tape and markers

    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_11_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
     to
    0.75
    <0x0D>
    0.59
    -
    0.57
     as
    0.55
     aisle
    0.55
    '
    0.52
     users
    0.51
     on
    0.50
     np
    0.49
     rooting
    0.48
    POSITIVE LOGITS
    كَ
    0.49
     넘어
    0.47
    bulldozer
    0.46
     بواسطة
    0.46
     اله
    0.45
     následuj
    0.45
    衍
    0.45
    يث
    0.45
    ához
    0.44
    derr
    0.44
    Activations Density 0.005%

    No Known Activations