© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139185
    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_12_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
    uje
    0.64
     "
    0.57
    ле
    0.55
     Competitive
    0.54
    ار
    0.54
    全面的
    0.53
    ↵↵
    0.51
    ्रांत
    0.51
     Stephens
    0.51
     nurturing
    0.50
    POSITIVE LOGITS
    Could
    0.66
    could
    0.62
    하지만
    0.55
    Rim
    0.55
    Haven
    0.54
    처럼
    0.54
     μπορού
    0.54
    :]
    0.53
     mógł
    0.52
    차가
    0.52
    Activations Density 0.000%

    No Known Activations