© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208945
    Prev
    Next
    INDEX
    Explanations

    physical disturbances: shock, vibration, drops

    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_20_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
    一眼
    0.44
     タイヤ
    0.42
    matic
    0.42
    王朝
    0.42
    crawler
    0.41
     sprayed
    0.40
     이전
    0.40
     ద
    0.39
     ति
    0.39
    spray
    0.39
    POSITIVE LOGITS
     norepinephrine
    0.45
     Westport
    0.45
     "":
    0.44
    についての
    0.43
    いる
    0.43
    变成
    0.43
     अर्जुन
    0.43
     unsol
    0.43
     Princeton
    0.41
     ლი
    0.41
    Activations Density 0.000%

    No Known Activations