© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46177
    Prev
    Next
    INDEX
    Explanations

    burger buns

    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_13_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
    eosin
    0.45
    利
    0.45
    organised
    0.44
    iran
    0.44
    email
    0.43
    ky
    0.43
    स्या
    0.43
    Во
    0.42
    Dataset
    0.42
    arme
    0.42
    POSITIVE LOGITS
     burger
    0.62
     Burger
    0.60
     burgers
    0.49
     hamburger
    0.47
    р
    0.47
     la
    0.46
    🍔
    0.46
    acja
    0.45
     breads
    0.44
     balance
    0.44
    Activations Density 0.006%

    No Known Activations