© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234247
    Prev
    Next
    INDEX
    Explanations

    drowsiness or sedation

    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_32_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
     Unit
    0.41
     CRUD
    0.40
     moist
    0.39
     í
    0.39
     wet
    0.38
    潅
    0.38
     apresentação
    0.38
     sustenance
    0.38
    砒
    0.38
    ocular
    0.37
    POSITIVE LOGITS
     climb
    0.38
    ждению
    0.38
    Ђ
    0.37
    azers
    0.36
    èo
    0.35
     luck
    0.34
    ܠ
    0.34
    ั้ง
    0.34
     harvesting
    0.34
    ครื่อง
    0.34
    Activations Density 0.002%

    No Known Activations