© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34117
    Prev
    Next
    INDEX
    Explanations

    antioxidant compounds

    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_31_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
    impanan
    0.40
     appropriateness
    0.39
     कॉमर्स
    0.38
    ExternalTaskPojo
    0.38
    📛
    0.37
     multer
    0.37
     [](
    0.36
     хочу
    0.36
     लापर
    0.36
     ظِلِّ
    0.36
    POSITIVE LOGITS
     measurement
    0.36
    coh
    0.36
    採
    0.36
     notch
    0.34
    ungkan
    0.34
     elic
    0.34
     hole
    0.34
     neighbors
    0.34
    cco
    0.33
    젝
    0.33
    Activations Density 0.075%

    No Known Activations