© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45844
    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_22_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
    guys
    0.58
    https
    0.52
     superstars
    0.47
    rds
    0.46
    taker
    0.46
    neigh
    0.46
     ইহাতে
    0.46
    “
    0.46
    ک
    0.46
    THERE
    0.45
    POSITIVE LOGITS
     เช
    0.55
     面
    0.54
     غير
    0.50
    ál
    0.49
     εν
    0.48
     zullen
    0.48
     Pantheon
    0.47
     อาจ
    0.47
     té
    0.46
     Παν
    0.46
    Activations Density 0.000%

    No Known Activations