© 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. 6731
    Prev
    Next
    INDEX
    Explanations

    food craving order

    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
    出售
    0.42
     деко
    0.40
    𒁉
    0.38
     testAvg
    0.38
    风格
    0.38
    াগত
    0.38
     стиль
    0.37
    Minn
    0.37
     déco
    0.37
    🟣
    0.37
    POSITIVE LOGITS
     bur
    0.42
     craving
    0.38
     FEED
    0.38
     Discover
    0.37
     feed
    0.37
    পিং
    0.37
     Bur
    0.37
     grabbed
    0.36
     inde
    0.36
     crave
    0.36
    Activations Density 0.038%

    No Known Activations