© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7031
    Prev
    Next
    INDEX
    Explanations

    her cooking

    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_39_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
     civilisation
    0.41
     riff
    0.39
    ดื่ม
    0.39
     styl
    0.38
    Romantic
    0.37
     respiration
    0.37
     existential
    0.37
    ܛ
    0.37
     romant
    0.37
     нарко
    0.36
    POSITIVE LOGITS
     bake
    0.48
     baking
    0.44
    cook
    0.43
     cook
    0.43
     cookbooks
    0.42
    recipes
    0.41
     nấu
    0.41
     Bake
    0.41
    bake
    0.40
     recipes
    0.40
    Activations Density 0.089%

    No Known Activations