© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154662
    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_50_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
     Sur
    0.43
     deger
    0.41
    ဧ
    0.41
    Islam
    0.39
     જાહેર
    0.38
    埇
    0.38
     رح
    0.38
     като
    0.38
    ]=\
    0.37
    <unused84>
    0.37
    POSITIVE LOGITS
     officials
    0.73
     Officials
    0.73
    Officials
    0.70
     अधिकारियों
    0.63
    官员
    0.63
     офи
    0.57
    offic
    0.53
    ｵ
    0.53
     কর্মকর্তাদের
    0.52
     અધિકારી
    0.52
    Activations Density 0.000%

    No Known Activations