© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163002
    Prev
    Next
    INDEX
    Explanations

    clean label, Campylobacter

    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_31_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
     nutr
    0.44
     produt
    0.43
     lactose
    0.42
    "[
    0.41
     '[
    0.41
     Nutr
    0.40
     latte
    0.39
     Latte
    0.38
     מל
    0.37
     "[
    0.36
    POSITIVE LOGITS
    逖
    0.42
    켓
    0.40
    Glasses
    0.39
    quées
    0.39
     ficha
    0.39
    τια
    0.38
    неопр
    0.38
     perimeter
    0.37
     ورحمه
    0.36
     परिचाल
    0.36
    Activations Density 0.000%

    No Known Activations