© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54606
    Prev
    Next
    INDEX
    Explanations

    ice, freezing, and snow

    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_31_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
     뜨
    0.41
    뜨
    0.37
    锆
    0.36
     मेड
    0.35
     عامر
    0.35
     귀
    0.34
     பிரத
    0.34
     heatmap
    0.34
     неда
    0.34
     Partridge
    0.34
    POSITIVE LOGITS
     ice
    0.46
     MOM
    0.45
     Ice
    0.44
    Ice
    0.43
    冰
    0.42
     icy
    0.38
    氷
    0.38
     freezing
    0.38
    Mom
    0.37
     slush
    0.37
    Activations Density 0.027%

    No Known Activations