© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10662
    Prev
    Next
    INDEX
    Explanations

    column layout direction

    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
     city
    0.57
    0
    0.55
     City
    0.55
    ning
    0.54
    int
    0.54
     er
    0.53
     en
    0.52
    uring
    0.51
    1
    0.51
    imento
    0.51
    POSITIVE LOGITS
     :");
    0.65
    お願い致します
    0.61
    迠
    0.59
     inflación
    0.57
    :",
    0.55
    χ
    0.53
    헷
    0.53
    ",{
    0.52
     sprechen
    0.52
    注释
    0.52
    Activations Density 0.024%

    No Known Activations