© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33283
    Prev
    Next
    INDEX
    Explanations

    multi-tiered system model

    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_7_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
    да
    0.38
    le
    0.30
    ра
    0.30
    J
    0.29
    ле
    0.27
    м
    0.27
    لا
    0.27
    ى
    0.27
    도
    0.27
     перечис
    0.25
    POSITIVE LOGITS
     has
    0.30
    '
    0.29
     Á
    0.28
     Ces
    0.28
     Questa
    0.28
     Esta
    0.27
     Otros
    0.27
     Nh
    0.27
     Alberta
    0.27
     で
    0.27
    Activations Density 0.013%

    No Known Activations