© 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
    2. Gemma-3-27B-IT
    3. 43-GEMMASCOPE-2-TRANSCODER-262K
    4. 210487
    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_43_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
     কালো
    0.41
     black
    0.39
    queeze
    0.38
     Guz
    0.37
     mun
    0.37
     फोर्थ
    0.36
    🖤
    0.36
    ofi
    0.36
     instructor
    0.35
     Baird
    0.35
    POSITIVE LOGITS
    াজিক
    0.39
    Classpath
    0.37
    ^{-(
    0.37
    楶
    0.37
    ﮢ
    0.36
     закреп
    0.36
    諏
    0.36
    Arts
    0.35
    టా
    0.35
    鹑
    0.35
    Activations Density 0.000%

    No Known Activations