© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134138
    Prev
    Next
    INDEX
    Explanations

    outdoor activities

    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_50_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
     DR
    0.47
    Ⴚ
    0.44
     scaling
    0.39
     Scaling
    0.38
    Scaling
    0.35
     cruc
    0.34
     Od
    0.34
    িনার
    0.34
     தெளி
    0.34
    [
    0.33
    POSITIVE LOGITS
    ချိန်
    0.40
    pretty
    0.39
     pretty
    0.39
    衝撃
    0.39
    甲
    0.38
     मिथुन
    0.37
     स्मृति
    0.37
     સ્વ
    0.37
    颊
    0.37
    ogne
    0.36
    Activations Density 0.004%

    No Known Activations