© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12185
    Prev
    Next
    INDEX
    Explanations

    diet and eating habits

    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
    Not in Any Lists

    No Comments

    Negative Logits
    inerja
    0.40
    隶
    0.38
    athed
    0.38
     Tania
    0.37
    隷
    0.37
    Exchange
    0.36
     Dough
    0.36
     draped
    0.36
     thin
    0.35
     substantive
    0.35
    POSITIVE LOGITS
     eating
    0.54
     eaters
    0.47
     eats
    0.46
     diet
    0.46
    饮食
    0.46
    eating
    0.45
     elimination
    0.43
     Eating
    0.41
     eater
    0.41
    采
    0.40
    Activations Density 0.079%

    No Known Activations