© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170722
    Prev
    Next
    INDEX
    Explanations

    exponents like x^2

    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_20_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
    ➲
    0.37
     जन्म
    0.30
     cathode
    0.29
     těchto
    0.29
     टास्क
    0.29
     Visits
    0.29
     Kegiatan
    0.29
     Tecnologia
    0.29
    াভাবিক
    0.29
     বোপ
    0.28
    POSITIVE LOGITS
     under
    0.29
    a
    0.27
    y
    0.26
     because
    0.26
     сло
    0.26
    인지
    0.26
    をする
    0.25
    redo
    0.25
    aea
    0.25
     langu
    0.25
    Activations Density 0.001%

    No Known Activations