© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120878
    Prev
    Next
    INDEX
    Explanations

    omega-6 fatty acids

    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_27_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
    ঘাতে
    0.25
    贝
    0.25
    updates
    0.25
    oribus
    0.25
    更新
    0.24
    ފައި
    0.24
    睿
    0.24
    Arist
    0.23
     обновления
    0.23
    ®.
    0.23
    POSITIVE LOGITS
     eva
    0.23
     Movies
    0.22
     creeps
    0.22
     altern
    0.21
     woodwork
    0.21
     hear
    0.20
     elif
    0.20
     hotspots
    0.20
     knuckle
    0.20
     bump
    0.20
    Activations Density 0.006%

    No Known Activations