© 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. 227757
    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
    1.05
    রা
    1.02
     взя
    0.96
    um
    0.96
     reckless
    0.91
    ದ
    0.88
     murky
    0.87
    ।
    0.87
    the
    0.83
     hardworking
    0.80
    POSITIVE LOGITS
    (
    1.35
    \
    1.28
    ك
    1.27
    {
    1.16
    ي
    1.14
    ل
    1.05
    ادي
    1.00
    ان
    0.99
    א
    0.98
    尔
    0.94
    Activations Density 0.000%

    No Known Activations