© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261148
    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_5_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
    ا
    1.29
    ssä
    1.13
    та
    0.98
    to
    0.97
    یان
    0.96
    sion
    0.95
    ski
    0.94
    ம்
    0.92
     you
    0.91
    м
    0.91
    POSITIVE LOGITS
     in
    1.34
    '
    1.16
    ’
    0.97
     on
    0.96
    *
    0.96
    ate
    0.92
    ist
    0.91
     for
    0.91
     by
    0.88
    \
    0.86
    Activations Density 0.000%

    No Known Activations