© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82762
    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_0_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
     a
    1.13
     in
    0.98
     are
    0.97
     i
    0.76
    ized
    0.74
    ية
    0.73
    um
    0.70
    ,
    0.66
     I
    0.65
    5
    0.64
    POSITIVE LOGITS
    리
    1.08
    시
    0.92
    n
    0.91
    티
    0.88
    ラ
    0.80
    i
    0.78
    ли
    0.77
    that
    0.77
    伥
    0.77
    韫
    0.75
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.