© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43796
    Prev
    Next
    INDEX
    Explanations

    eucalyptus leaves and habitats

    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
    ad
    0.18
    監督
    0.18
    設立
    0.18
     học
    0.17
     dirigeants
    0.17
     receivable
    0.16
    図書館
    0.16
    '
    0.16
    ట
    0.16
     director
    0.16
    POSITIVE LOGITS
     polymers
    0.17
     sunflowers
    0.17
     geometries
    0.17
     amplifiers
    0.17
     cucumbers
    0.17
     nový
    0.17
     শাজ
    0.16
     drips
    0.16
     veggies
    0.16
    Meh
    0.16
    Activations Density 0.002%

    No Known Activations