© 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. 226870
    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_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
     of
    1.14
     is
    0.96
     to
    0.94
    вия
    0.93
    G
    0.89
     usu
    0.86
    тся
    0.85
    R
    0.84
    ной
    0.83
     with
    0.82
    POSITIVE LOGITS
    ot
    1.06
    もら
    1.00
    在
    0.88
    also
    0.82
    ও
    0.80
    ovány
    0.79
    ↵
    0.77
    و
    0.75
    arı
    0.74
     தலைமையில்
    0.74
    Activations Density 0.000%

    No Known Activations