© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124041
    Prev
    Next
    INDEX
    Explanations

    engine idling

    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
     মুজিবের
    0.40
    flood
    0.38
     سەر
    0.38
     Poss
    0.37
    雕
    0.37
    ုပ်
    0.37
    eful
    0.36
    pluck
    0.36
    uller
    0.35
     circumference
    0.35
    POSITIVE LOGITS
     idle
    1.34
     idling
    1.20
    Idle
    1.18
     Idle
    1.18
    idle
    1.05
    闲
    0.77
    閒
    0.70
     Id
    0.61
    アイドル
    0.61
    閑
    0.61
    Activations Density 0.002%

    No Known Activations