© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196482
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
     그는
    0.47
     biologist
    0.47
     bike
    0.46
    proble
    0.46
     boat
    0.45
    彼は
    0.45
     прадстаў
    0.44
    ी
    0.44
    ย
    0.44
    <0xE9>
    0.44
    POSITIVE LOGITS
    ranno
    0.52
    lıkla
    0.50
     Ни
    0.50
     Chiropractic
    0.47
     Великобрита
    0.47
     Summ
    0.46
     Montréal
    0.46
    r
    0.46
    LocalAppData
    0.45
     Making
    0.45
    Activations Density 0.000%

    No Known Activations