© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3812
    Prev
    Next
    INDEX
    Explanations

    document.querySelector or similar

    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_40_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
    ೈಸ
    0.39
    फेक्शन
    0.38
    豔
    0.37
    艷
    0.37
    Scop
    0.37
    SizePolicy
    0.36
    كنولوج
    0.36
    версите
    0.36
    enschap
    0.36
    伈
    0.35
    POSITIVE LOGITS
     document
    0.77
    document
    0.73
     query
    0.65
     dokument
    0.62
     Document
    0.62
    query
    0.61
     documents
    0.60
     dokumen
    0.59
     queries
    0.58
    Document
    0.57
    Activations Density 0.169%

    No Known Activations