© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164309
    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_13_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
    adeloupe
    0.50
    infodisc
    0.48
    ഭം
    0.48
    哫
    0.48
    Pyrazole
    0.48
    ffiti
    0.47
    rät
    0.46
    dbThoughtData
    0.46
     أي
    0.46
     διο
    0.46
    POSITIVE LOGITS
     why
    0.54
    м
    0.51
     costs
    0.50
    m
    0.50
     how
    0.48
     things
    0.48
     does
    0.47
     types
    0.47
    things
    0.46
     Why
    0.46
    Activations Density 0.000%

    No Known Activations