© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11697
    Prev
    Next
    INDEX
    Explanations

    compaction definition

    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_13_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
     won
    0.55
    -
    0.50
    {
    0.50
     stall
    0.48
     shielded
    0.48
     immense
    0.48
     names
    0.47
    ċ
    0.47
     nombre
    0.47
     senior
    0.47
    POSITIVE LOGITS
    Hitting
    0.53
     مشکلات
    0.53
    Breaking
    0.52
    Hashing
    0.50
     قواعد
    0.49
    Looking
    0.49
     بیشتر
    0.49
    Raising
    0.48
    𝑁
    0.48
    Broken
    0.47
    Activations Density 0.021%

    No Known Activations