© 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. 132433
    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
    не
    1.13
    ف
    0.87
     for
    0.86
     an
    0.84
     was
    0.84
    و
    0.81
    ால
    0.79
     been
    0.79
    0
    0.78
    ு
    0.77
    POSITIVE LOGITS
    (
    1.50
    -
    1.19
    ra
    1.05
    i
    1.02
    -/
    0.96
    >
    0.95
    -”
    0.94
    σεις
    0.90
    .>
    0.90
    ’
    0.90
    Activations Density 0.000%

    No Known Activations