© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39505
    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_11_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
    ва
    0.59
     humbly
    0.58
    ține
    0.57
    ваемых
    0.57
    ρεί
    0.56
     Cenomanian
    0.55
    牫
    0.55
    țiunea
    0.55
    的には
    0.54
     consape
    0.54
    POSITIVE LOGITS
    X
    0.65
    Le
    0.63
    Je
    0.63
    H
    0.62
    LE
    0.61
    Tr
    0.61
    F
    0.61
    Ch
    0.61
     e
    0.60
    Z
    0.60
    Activations Density 0.000%

    No Known Activations