© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58617
    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
     for
    0.99
     H
    0.94
    (
    0.89
     F
    0.89
    ช่วง
    0.87
     G
    0.85
     R
    0.84
     breed
    0.82
     half
    0.82
     flexible
    0.81
    POSITIVE LOGITS
    ری
    1.85
    ا
    1.77
    ре
    1.61
    ના
    1.55
    It
    1.52
    om
    1.48
    아
    1.48
    ح
    1.47
    ри
    1.43
    ون
    1.40
    Activations Density 0.000%

    No Known Activations