© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197231
    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_4_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
    ك
    0.82
    บ
    0.67
    ن
    0.66
    D
    0.64
    ch
    0.64
    ка
    0.62
    sama
    0.62
    י
    0.61
    et
    0.57
    ش
    0.57
    POSITIVE LOGITS
    ۔
    0.69
    ।
    0.68
    ።
    0.68
    。
    0.66
    $.
    0.62
    ě
    0.61
    ។
    0.57
    кси
    0.54
    isers
    0.54
    ᱤ
    0.54
    Activations Density 0.000%

    No Known Activations