© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246093
    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_40_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
     antid
    0.38
    Л
    0.37
    긴
    0.37
     stockno
    0.36
     항
    0.35
    WOM
    0.35
     sympath
    0.35
     sympathies
    0.34
    $/../../
    0.34
    jó
    0.34
    POSITIVE LOGITS
     Arcadia
    0.40
     Transparency
    0.40
     Frederic
    0.38
     secre
    0.36
     Tan
    0.36
     arc
    0.36
     Forbes
    0.35
     coldest
    0.35
    ອາ
    0.35
     شرا
    0.35
    Activations Density 0.000%

    No Known Activations