© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29080
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    et
    0.95
    /
    0.84
    는
    0.80
    ت
    0.76
    {
    0.75
    т
    0.73
    _
    0.71
    "
    0.70
    )$
    0.70
     всю
    0.69
    POSITIVE LOGITS
     jihad
    0.82
    యత్
    0.78
     Routledge
    0.76
     lighthouse
    0.74
    志
    0.74
     naan
    0.73
     ”
    0.73
    ভিক্ষ
    0.73
    نه
    0.72
     Meesho
    0.72
    Activations Density 0.000%

    No Known Activations