© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60255
    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_2_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
    1.37
    ۹
    0.98
     in
    0.96
    you
    0.95
    ේ
    0.95
    isn
    0.94
    iska
    0.89
    defi
    0.86
    ని
    0.86
    fler
    0.85
    POSITIVE LOGITS
    ور
    1.43
    ле
    1.18
    ロ
    1.02
    ’
    0.99
    一
    0.98
    手
    0.96
     hoge
    0.95
     excelled
    0.92
    에
    0.92
    те
    0.91
    Activations Density 0.000%

    No Known Activations