© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82029
    Prev
    Next
    INDEX
    Explanations

    會 + verb/noun

    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_0_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
     for
    2.06
    5
    2.02
    4
    1.95
    at
    1.76
    for
    1.70
    р
    1.69
    6
    1.52
    ר
    1.52
    3
    1.52
    К
    1.42
    POSITIVE LOGITS
    ك
    1.46
     ہے۔
    1.45
    ۔
    1.43
    מ
    1.41
    是
    1.37
    その
    1.36
    は
    1.36
    이면
    1.29
    이었다
    1.28
    은
    1.27
    Activations Density 0.000%

    No Known Activations