© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24924
    Prev
    Next
    INDEX
    Explanations

    sinking

    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_56_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
    물
    1.78
    물을
    1.02
    物
    0.98
    물의
    0.93
    물이
    0.87
     물
    0.85
    物的
    0.80
    勿
    0.77
    物の
    0.67
     vật
    0.65
    POSITIVE LOGITS
     sinking
    2.09
     sank
    1.30
     sinks
    1.18
     gn
    1.18
     sunk
    1.15
     sink
    1.13
    sink
    1.05
     sneaking
    1.03
    Sink
    0.98
     nagging
    0.98
    Activations Density 0.061%

    No Known Activations