© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29848
    Prev
    Next
    INDEX
    Explanations

    burger ingredients

    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_40_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
    ubber
    0.41
    هِ
    0.41
     Α
    0.38
     Ә
    0.38
     beets
    0.36
    henium
    0.36
     อ
    0.36
     screws
    0.36
     déchir
    0.35
     dampers
    0.34
    POSITIVE LOGITS
    getSession
    0.39
    forcements
    0.38
    ולד
    0.38
     количестве
    0.37
    灶
    0.37
     sauve
    0.36
    createNew
    0.36
     southeast
    0.36
     ইমেজ
    0.36
     közé
    0.34
    Activations Density 0.007%

    No Known Activations