© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234562
    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_32_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
    EOUS
    0.39
    </iframe>
    0.38
    proof
    0.37
    rived
    0.37
     lading
    0.36
    hears
    0.36
    laden
    0.36
    ivu
    0.36
     கூடு
    0.35
     dialog
    0.35
    POSITIVE LOGITS
     வர
    0.39
     कमा
    0.37
     สง
    0.37
     size
    0.37
    ⅜
    0.37
     pes
    0.37
     Berc
    0.36
     کسب
    0.36
    Batter
    0.35
     diminu
    0.35
    Activations Density 0.000%

    No Known Activations