© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 63736
    Prev
    Next
    INDEX
    Explanations

    bottled water

    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_41_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
     STYLE
    0.43
     ken
    0.41
     लाइब्रेरी
    0.41
    LIBRARY
    0.37
     스타일
    0.36
    STYLE
    0.36
     trag
    0.36
    犀
    0.36
    鎿
    0.35
     Пари
    0.35
    POSITIVE LOGITS
     bottled
    1.66
     bottling
    1.59
    bott
    1.49
     Bott
    1.48
     bott
    1.45
    Bott
    1.44
    瓶
    1.06
     bottles
    1.05
     bottle
    1.04
    Bottle
    0.97
    Activations Density 0.031%

    No Known Activations