© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200837
    Prev
    Next
    INDEX
    Explanations

    tied with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    ות
    1.40
     that
    1.11
    ↵↵
    1.01
    л
    0.98
     this
    0.98
    is
    0.96
    ()=>{
    0.90
    ז
    0.85
    จะ
    0.85
     Ising
    0.84
    POSITIVE LOGITS
     in
    1.06
    िन
    1.04
    もら
    0.95
     في
    0.88
     सफाया
    0.85
    ในช่วง
    0.85
    在
    0.84
     παιδιά
    0.81
    <unused753>
    0.80
    CT
    0.79
    Activations Density 0.008%

    No Known Activations