© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61748
    Prev
    Next
    INDEX
    Explanations

    New Mexico

    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
    opolymers
    0.64
    UMIRE
    0.63
    óloga
    0.62
    。</
    0.60
     张
    0.58
     نئے
    0.57
    ôme
    0.57
     ہے۔
    0.57
    俔
    0.57
    OUIS
    0.56
    POSITIVE LOGITS
    $
    0.54
     .
    0.54
    {
    0.54
     =
    0.51
     diing
    0.51
     {
    0.50
     //
    0.49
    კ
    0.49
    เท้า
    0.48
     )
    0.47
    Activations Density 0.000%

    No Known Activations