© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160615
    Prev
    Next
    INDEX
    Explanations

    syndrome, singers, (roman)

    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_2_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
    ı
    0.97
    ۔
    0.91
    。「
    0.89
    ü
    0.85
    ид
    0.84
    и
    0.82
    า
    0.81
    "।
    0.78
    なります
    0.76
    on
    0.75
    POSITIVE LOGITS
    ק
    1.11
    ش
    1.10
    0
    1.02
    ח
    1.00
    ม
    0.95
    s
    0.92
    ש
    0.91
    স
    0.91
    ج
    0.89
    ส
    0.88
    Activations Density 0.001%

    No Known Activations