© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59727
    Prev
    Next
    INDEX
    Explanations

    traffic light colors

    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
    йти
    0.56
     מ
    0.52
     голо
    0.52
    นี้
    0.51
     молит
    0.51
     ম
    0.49
     ко
    0.49
     انقلاب
    0.48
     अगु
    0.48
    เหล่านี้
    0.48
    POSITIVE LOGITS
    然
    0.62
    eras
    0.54
     taxi
    0.52
    版权
    0.52
     so
    0.51
    ZA
    0.49
    垂直
    0.49
     planis
    0.49
     sone
    0.49
     deer
    0.48
    Activations Density 0.029%

    No Known Activations