© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118847
    Prev
    Next
    INDEX
    Explanations

    .com and .es suffixes

    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_27_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
     taill
    0.38
    导致
    0.38
    🥔
    0.37
    🥊
    0.35
     रोटी
    0.35
    SUV
    0.34
    從
    0.34
     gelijk
    0.34
    从中
    0.34
    <0xD9>
    0.34
    POSITIVE LOGITS
     Qatar
    0.46
     Brid
    0.41
     Terms
    0.41
     Denmark
    0.39
     Contact
    0.38
     Cebu
    0.38
     Management
    0.38
     Council
    0.37
     Iceland
    0.37
     Compet
    0.37
    Activations Density 0.002%

    No Known Activations