© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24501
    Prev
    Next
    INDEX
    Explanations

    fill in the blanks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     [
    0.70
     \[
    0.68
     XXX
    0.68
     $[
    0.67
     xxx
    0.66
     '[
    0.59
     /
    0.57
     ______
    0.55
     _______
    0.55
     {
    0.55
    POSITIVE LOGITS
    aggregation
    0.39
    ’.
    0.38
     خوف
    0.36
    sorption
    0.35
    iformis
    0.35
    tickers
    0.34
    Aggregation
    0.34
     کہنا
    0.33
     বৃদ্ধির
    0.33
    §
    0.33
    Activations Density 0.003%

    No Known Activations