© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5037
    Prev
    Next
    INDEX
    Explanations

    poetic Chinese imagery sword fighting

    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
    治療
    0.36
    穩定
    0.35
    샅
    0.34
    䧏
    0.34
    沇
    0.33
    鮒
    0.33
    ⤠
    0.32
    勂
    0.32
    賚
    0.32
    сіі
    0.31
    POSITIVE LOGITS
    玉
    0.30
    WP
    0.30
     WP
    0.29
    UG
    0.27
      
    0.27
     embedded
    0.27
     perform
    0.27
     Fu
    0.26
     screw
    0.26
     pinch
    0.25
    Activations Density 0.012%

    No Known Activations