© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 63740
    Prev
    Next
    INDEX
    Explanations

    lung | lunges | lunging

    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_41_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
     incomplete
    0.49
    incomplete
    0.48
     incomple
    0.47
    .$.
    0.41
    콤
    0.39
    webhook
    0.39
    ▩
    0.38
     Proctor
    0.38
    unfinished
    0.37
    ifications
    0.36
    POSITIVE LOGITS
     lung
    1.50
     Lung
    1.31
    Lung
    1.26
    lung
    1.11
    肺
    1.00
     lungs
    0.95
     l
    0.75
     pulmonary
    0.72
     lun
    0.70
     நுரையீரல்
    0.68
    Activations Density 0.004%

    No Known Activations