© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129477
    Prev
    Next
    INDEX
    Explanations

    Emmanuel Macron

    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_6_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
     was
    0.91
     to
    0.85
    د
    0.79
     be
    0.76
     for
    0.75
    ى
    0.74
     It
    0.73
    ж
    0.72
    т
    0.71
    et
    0.71
    POSITIVE LOGITS
    在
    0.79
    ও
    0.78
    their
    0.73
    ໃນ
    0.71
     σε
    0.70
    Α
    0.68
     других
    0.67
    :
    0.67
    theta
    0.64
    ↵
    0.64
    Activations Density 0.000%

    No Known Activations