© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200910
    Prev
    Next
    INDEX
    Explanations

    cooking or chef

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     대
    0.45
     ໜ
    0.43
     رہتے
    0.43
     Cat
    0.42
    ूण
    0.40
    үр
    0.40
     Prints
    0.39
     红
    0.39
     印
    0.39
     Supplier
    0.38
    POSITIVE LOGITS
     cooking
    0.49
     cooks
    0.48
     kitchens
    0.47
    Chef
    0.46
    ครัว
    0.45
    Cooking
    0.44
     cocina
    0.44
    cook
    0.43
    chef
    0.42
     chef
    0.41
    Activations Density 0.001%

    No Known Activations