© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10711
    Prev
    Next
    INDEX
    Explanations

    electromagnetic fields and effects

    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_40_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
    やす
    0.40
    yaan
    0.39
    姥
    0.38
     pounded
    0.37
     Gant
    0.37
     भाषण
    0.37
    faat
    0.36
    ాడు
    0.36
    演讲
    0.36
    禕
    0.35
    POSITIVE LOGITS
    Electric
    1.06
     electric
    1.05
     Electric
    1.04
     ELECTRIC
    0.92
     electrostatic
    0.91
     magnetic
    0.91
    electric
    0.89
     Magnetic
    0.88
    Magnetic
    0.88
    ELECTRIC
    0.83
    Activations Density 0.084%

    No Known Activations