© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165336
    Prev
    Next
    INDEX
    Explanations

    mercantilism, tax, labor, wealth

    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_31_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
     ``
    0.44
     metros
    0.39
    ``
    0.39
     angeles
    0.38
    均衡
    0.38
     heat
    0.37
     Appalach
    0.37
     экономи
    0.36
     Entrepreneur
    0.35
     rates
    0.35
    POSITIVE LOGITS
     hôn
    0.44
     Suy
    0.43
     bulan
    0.40
    獐
    0.39
    рных
    0.38
     গ্রহন
    0.38
    Suy
    0.38
     Viên
    0.38
    टे
    0.38
    OfMonth
    0.38
    Activations Density 0.006%

    No Known Activations