© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139121
    Prev
    Next
    INDEX
    Explanations

    Flow, Rock, soft corals, Pacific region

    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_12_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
     प्रोटे
    0.27
    丽
    0.27
    PackageManager
    0.26
    鷗
    0.26
    Blend
    0.25
    ওয়
    0.25
    Florence
    0.25
    预防
    0.25
    D
    0.25
    lication
    0.24
    POSITIVE LOGITS
     MILLER
    0.28
     फैली
    0.28
     Reeves
    0.27
    memset
    0.27
    പ്പെട്ട
    0.26
     Peirce
    0.26
     ПП
    0.26
    ຕ້ອງ
    0.26
     vencedor
    0.26
    classify
    0.26
    Activations Density 0.000%

    No Known Activations