© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89819
    Prev
    Next
    INDEX
    Explanations

    chiplet designs, architecture, firmware

    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_3_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
    I
    0.93
    h
    0.90
    و
    0.78
    嶆
    0.73
    ار
    0.70
    ंना
    0.70
    нах
    0.67
    ع
    0.67
    戞
    0.66
    لت
    0.66
    POSITIVE LOGITS
     for
    1.03
     في
    0.98
    4
    0.97
     be
    0.96
    for
    0.89
    5
    0.80
     دي
    0.79
     فيلم
    0.77
     mộ
    0.75
     problém
    0.74
    Activations Density 0.004%

    No Known Activations