© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166781
    Prev
    Next
    INDEX
    Explanations

    sleeping

    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_34_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
    راه
    0.34
    kPa
    0.34
    峽
    0.33
    絬
    0.33
     problemlos
    0.33
     przech
    0.33
    حده
    0.33
    峡
    0.33
     hiked
    0.32
     aboriginal
    0.32
    POSITIVE LOGITS
    眠
    0.37
     Sleeping
    0.36
    భవ
    0.36
    Sleep
    0.34
     sleep
    0.34
     Sleep
    0.33
    Sleeping
    0.32
     Kisi
    0.32
     sleeping
    0.31
    睡眠
    0.31
    Activations Density 0.000%

    No Known Activations