© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121600
    Prev
    Next
    INDEX
    Explanations

    label for

    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Won
    0.32
     won
    0.30
    ，
    0.28
     fi
    0.27
    冒
    0.27
    crates
    0.26
     Faced
    0.26
     выигра
    0.26
     Won
    0.26
    won
    0.25
    POSITIVE LOGITS
     باي
    0.32
     cheeky
    0.31
     Tama
    0.31
    )>=
    0.31
     सेकेंडरी
    0.30
    නව
    0.30
     કરવાનો
    0.29
    掎
    0.29
     BASIS
    0.29
     посетить
    0.29
    Activations Density 0.001%

    No Known Activations