© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134992
    Prev
    Next
    INDEX
    Explanations

    sofa bed, air mattress, sleeping areas

    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_37_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
    鲵
    0.44
    纍
    0.39
    动态
    0.38
     Zeitpunkt
    0.37
    িমূলক
    0.36
    脣
    0.36
    Taxi
    0.35
     বিজে
    0.35
    かと
    0.35
     wounding
    0.35
    POSITIVE LOGITS
     sleeping
    1.20
     slept
    1.04
    sleeping
    1.04
     Sleeping
    1.00
    Sleeping
    0.98
     sleep
    0.98
     sofa
    0.95
     sleeps
    0.95
     bedding
    0.94
    睡
    0.92
    Activations Density 0.000%

    No Known Activations