© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11201
    Prev
    Next
    INDEX
    Explanations

    standing while performing physical activity

    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_13_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
    ंगाना
    0.47
     君
    0.47
     CFO
    0.47
    monotonic
    0.47
     lounge
    0.45
     Monk
    0.45
    杂志
    0.45
     座
    0.45
    盅
    0.44
    ऊस
    0.43
    POSITIVE LOGITS
     U
    0.52
     G
    0.52
     enraged
    0.51
    En
    0.50
     fossils
    0.50
     obsessed
    0.49
     H
    0.47
     музе
    0.47
     heritage
    0.47
     April
    0.47
    Activations Density 0.028%

    No Known Activations