© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127421
    Prev
    Next
    INDEX
    Explanations

    eat nutritious food

    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_37_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
     bip
    0.40
     Stanis
    0.37
    咏
    0.37
     menget
    0.36
     Variablen
    0.36
     master
    0.36
    .~\
    0.35
     leveling
    0.35
    欷
    0.35
     schak
    0.35
    POSITIVE LOGITS
     carrots
    0.42
     carrot
    0.42
     sweets
    0.39
    财政
    0.39
     turnips
    0.39
     nutrient
    0.38
     penggunaan
    0.38
    nutrient
    0.38
    qrt
    0.38
    🍭
    0.38
    Activations Density 0.002%

    No Known Activations