© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4524
    Prev
    Next
    INDEX
    Explanations

    food and eating

    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
     food
    2.02
     yemek
    1.98
    食べ
    1.97
     comida
    1.90
     eating
    1.89
     makanan
    1.88
    食
    1.88
     食
    1.84
    Eating
    1.84
    食物
    1.83
    POSITIVE LOGITS
    癃
    0.41
    ழ்க
    0.41
    StatusBadRequest
    0.39
    蕲
    0.38
    ल्लिंग
    0.38
    atology
    0.38
    鄢
    0.36
     MonoBehaviour
    0.36
     Heming
    0.36
    idcoin
    0.35
    Activations Density 0.093%

    No Known Activations