© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229707
    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
     for
    1.13
    ’
    0.98
    ut
    0.97
     (
    0.94
     типу
    0.92
    us
    0.89
     Ν
    0.88
    OCO
    0.84
     Abelian
    0.84
     gingham
    0.82
    POSITIVE LOGITS
    s
    1.08
    ों
    1.05
    that
    0.97
    دي
    0.96
    اي
    0.96
    단
    0.96
    ادي
    0.96
    н
    0.95
    ياء
    0.95
    ો
    0.95
    Activations Density 0.000%

    No Known Activations