© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247541
    Prev
    Next
    INDEX
    Explanations

    low and high contexts

    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_40_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
    䯩
    0.46
     عالية
    0.42
     low
    0.41
     high
    0.41
    低
    0.37
    ⾼
    0.37
     lying
    0.35
     High
    0.35
    ီး
    0.35
     低
    0.35
    POSITIVE LOGITS
     Shum
    0.38
     Chum
    0.35
     komunitas
    0.35
    Layer
    0.34
    クマ
    0.34
     saja
    0.33
     SAR
    0.32
    Maya
    0.32
    ほ
    0.32
    stuff
    0.32
    Activations Density 0.005%

    No Known Activations