© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175234
    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_20_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
    ne
    0.64
    na
    0.57
    l
    0.57
    v
    0.55
    us
    0.52
    m
    0.52
    all
    0.52
    *
    0.52
     sister
    0.51
    el
    0.51
    POSITIVE LOGITS
     documental
    0.49
    IVACON
    0.47
    歿
    0.47
    макраты
    0.46
     semblable
    0.46
     ServicePolicy
    0.46
    अरविंद
    0.46
     copyspace
    0.46
    MDEwOlJlcG
    0.46
     conoscenze
    0.46
    Activations Density 0.000%

    No Known Activations