© 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
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 3884
    Prev
    Next
    INDEX
    Explanations

    ROS code

    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_39_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
     অপহরণকারীদের
    0.37
    encoder
    0.36
    ధం
    0.35
     механи
    0.35
    RefManager
    0.35
    ഴ
    0.35
    ี้
    0.35
     mechanics
    0.34
    ඩු
    0.34
    Ε
    0.34
    POSITIVE LOGITS
     Turt
    0.41
     turtles
    0.40
     Velocity
    0.40
     ActionListener
    0.38
    Copper
    0.38
     existencia
    0.37
    鲐
    0.37
     Spring
    0.37
     入り
    0.37
     ROS
    0.37
    Activations Density 0.013%

    No Known Activations