© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176116
    Prev
    Next
    INDEX
    Explanations

    food occasions: meal, snack, dish

    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_20_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
     surviving
    0.43
    da
    0.42
      
    0.42
     held
    0.41
    ad
    0.41
     ring
    0.40
    1
    0.40
    pragma
    0.39
    inda
    0.39
     Lyndon
    0.38
    POSITIVE LOGITS
    ريبي
    0.45
     guerras
    0.44
     почув
    0.44
     তিনিই
    0.44
    чивать
    0.43
     খুঁজতে
    0.42
    /#{
    0.42
    彼女
    0.42
    痧
    0.42
     சுத்த
    0.42
    Activations Density 0.003%

    No Known Activations