© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15985
    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
    をする
    0.40
    CBC
    0.40
     Chir
    0.39
    Attached
    0.39
     Careers
    0.37
     する
    0.37
     بدور
    0.37
    ਭ
    0.37
     careers
    0.37
    ১২
    0.37
    POSITIVE LOGITS
     चाल
    0.38
    colonial
    0.36
     farmac
    0.36
     effic
    0.35
    Method
    0.35
    рован
    0.35
     NIST
    0.35
    Farmers
    0.35
     Prob
    0.35
     Buyers
    0.35
    Activations Density 0.000%

    No Known Activations