© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60259
    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_2_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
    ۰
    0.82
    sembles
    0.78
    gares
    0.73
     인한
    0.72
    
    0.71
    cnica
    0.70
     ='
    0.66
     impeding
    0.66
     август
    0.66
    fgets
    0.66
    POSITIVE LOGITS
    는
    1.18
    ת
    1.13
    ة
    1.05
    是
    1.04
    は
    0.97
    т
    0.93
    కు
    0.92
    ή
    0.87
     on
    0.86
    ו
    0.86
    Activations Density 0.000%

    No Known Activations