© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43676
    Prev
    Next
    INDEX
    Explanations

    occupies or is near space

    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_13_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
    郸
    0.50
    ourses
    0.50
    ə
    0.50
    }&\
    0.48
    ées
    0.47
    wisdom
    0.47
    יר
    0.47
    ul
    0.45
    蛏
    0.44
    ور
    0.44
    POSITIVE LOGITS
     tathapi
    0.47
    t
    0.46
     tenant
    0.43
     forested
    0.43
    ዐይን
    0.40
     flooring
    0.39
     Tile
    0.39
     przestr
    0.39
    瓷
    0.39
     pastor
    0.39
    Activations Density 0.062%

    No Known Activations