© 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
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 62711
    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_41_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
    絣
    0.37
    vim
    0.36
     مگر
    0.36
    汾
    0.36
    ecer
    0.36
    飛ば
    0.36
    ফার
    0.35
    stven
    0.35
     Hershey
    0.35
    <unused12>
    0.34
    POSITIVE LOGITS
     náklady
    0.52
     düşük
    0.42
     täht
    0.42
    ܢܐ
    0.39
     COST
    0.39
     Zero
    0.39
     rendah
    0.39
    鬨
    0.39
     जीरो
    0.39
     laag
    0.38
    Activations Density 0.000%

    No Known Activations