© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211512
    Prev
    Next
    INDEX
    Explanations

    kneeling

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     এড
    0.46
     জাতিসংঘের
    0.39
    ροι
    0.37
    DELTA
    0.36
    笛
    0.36
    的游戏
    0.35
     отме
    0.35
    掮
    0.35
    簍
    0.35
     сент
    0.34
    POSITIVE LOGITS
     kneeling
    1.63
     kneel
    1.63
     knelt
    1.48
     Kne
    1.41
    跪
    1.39
    kne
    1.35
     bowing
    1.30
     knee
    1.29
     knees
    1.29
     kne
    1.27
    Activations Density 0.003%

    No Known Activations