© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16686
    Prev
    Next
    INDEX
    Explanations

    power query controller

    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_40_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
    emor
    0.36
    IPLE
    0.36
     polypeptide
    0.36
    ಐ
    0.36
     Keyword
    0.36
     Pops
    0.35
    精密
    0.35
    酩
    0.35
    Keyword
    0.34
     ಎರಡ
    0.34
    POSITIVE LOGITS
    控制器
    0.46
     컨트롤
    0.40
     unsub
    0.40
    controller
    0.39
    eagle
    0.38
     controlling
    0.38
     связи
    0.38
     ABC
    0.38
    கூ
    0.38
     controller
    0.38
    Activations Density 0.037%

    No Known Activations