© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16728
    Prev
    Next
    INDEX
    Explanations

    response object

    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_15_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
     couches
    0.48
    haul
    0.45
    CR
    0.45
    fier
    0.44
     ממש
    0.43
    ینڈ
    0.42
    टन
    0.41
    渦
    0.41
    鑑定
    0.41
     CR
    0.41
    POSITIVE LOGITS
     njihov
    0.57
    '?
    0.55
    با
    0.50
    Kako
    0.50
     OutputStream
    0.49
    
    0.48
    ጶ
    0.48
     ihre
    0.47
    matical
    0.47
    زي
    0.46
    Activations Density 0.001%

    No Known Activations