© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4050
    Prev
    Next
    INDEX
    Explanations

    object detection and computer vision

    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
    スム
    0.42
     birbirinden
    0.40
    斤
    0.40
     বাম
    0.39
     perioada
    0.39
     суме
    0.39
     testigos
    0.38
    蕁
    0.38
     लिहाज
    0.38
    LEFT
    0.38
    POSITIVE LOGITS
     Vimeo
    0.40
    globe
    0.40
     scene
    0.39
     Coke
    0.39
    อง
    0.39
     kite
    0.39
    scenes
    0.39
     Bott
    0.38
     scenes
    0.38
    Globe
    0.38
    Activations Density 0.120%

    No Known Activations