© 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. 134752
    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
    al
    1.34
     invigorating
    0.89
    anjutkan
    0.88
    ン
    0.87
    امین
    0.86
    ์
    0.85
    ᱐
    0.85
    alike
    0.83
    ード
    0.82
    larının
    0.81
    POSITIVE LOGITS
    '
    0.79
     zwar
    0.77
     get
    0.74
     ben
    0.73
    ，
    0.72
     questo
    0.71
    لي
    0.71
    ella
    0.70
     da
    0.70
     mitigate
    0.70
    Activations Density 0.000%

    No Known Activations