© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130822
    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_6_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
     for
    0.84
    出
    0.73
    手
    0.72
    يد
    0.70
     é
    0.68
    多
    0.67
    ó
    0.65
    高
    0.65
    一部
    0.64
    安
    0.64
    POSITIVE LOGITS
    dır
    0.90
    the
    0.85
    ის
    0.77
    thed
    0.77
    ש
    0.76
    Name
    0.74
    os
    0.73
    they
    0.73
    tn
    0.72
    0
    0.71
    Activations Density 0.000%

    No Known Activations