© 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. 231451
    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
     It
    1.04
    م
    1.04
     You
    1.00
    н
    0.99
    з
    0.97
     to
    0.95
     effectuer
    0.95
    ն
    0.94
     át
    0.93
     américain
    0.93
    POSITIVE LOGITS
    3
    1.35
    2
    1.12
    7
    1.06
    4
    1.04
    global
    0.99
    ین
    0.98
    に
    0.98
    에
    0.93
    8
    0.91
    aları
    0.85
    Activations Density 0.000%

    No Known Activations