© 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. 5002
    Prev
    Next
    INDEX
    Explanations

    chuckled, smiled, laughed

    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
    籌
    0.43
    çu
    0.42
     primarySwatch
    0.42
     მან
    0.41
    反應
    0.41
    漳
    0.40
    iminaries
    0.39
    잘
    0.39
    稅
    0.39
     अभिकारक
    0.39
    POSITIVE LOGITS
     nodded
    0.46
     nodding
    0.38
     nod
    0.38
    点了点头
    0.38
     rubbing
    0.38
     Traction
    0.37
    Push
    0.37
     Cliquez
    0.37
    Children
    0.37
     mice
    0.36
    Activations Density 0.021%

    No Known Activations