© 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. 201149
    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
    .
    1.09
    s
    1.05
    '
    0.95
    AST
    0.88
    es
    0.85
    im
    0.84
    AI
    0.84
    ции
    0.81
    AU
    0.80
    ों
    0.80
    POSITIVE LOGITS
     ي
    1.21
     acht
    1.13
    ية
    1.09
     unseren
    1.00
     andere
    1.00
     Í
    0.99
     Über
    0.98
     agus
    0.97
     wordt
    0.96
     Před
    0.96
    Activations Density 0.000%

    No Known Activations