© 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. 10823
    Prev
    Next
    INDEX
    Explanations

    corpus and databases

    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
     próprio
    0.54
    irectional
    0.52
    linien
    0.52
    ਕੇ
    0.51
    variant
    0.50
    тите
    0.49
    ";
    0.48
    το
    0.48
    ли
    0.47
    менно
    0.47
    POSITIVE LOGITS
     database
    0.61
    WordArray
    0.57
    Wales
    0.55
    溲
    0.53
     같아요
    0.52
    📕
    0.52
     Wales
    0.50
     Sayles
    0.50
     ngay
    0.50
     Database
    0.49
    Activations Density 0.047%

    No Known Activations