© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37031
    Prev
    Next
    INDEX
    Explanations

    generate creative text

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     रै
    0.37
    itemBackground
    0.36
    ऽ
    0.36
    سٹر
    0.35
    xm
    0.35
     gallium
    0.35
     '">'
    0.35
    ktu
    0.35
    agogues
    0.35
     xm
    0.34
    POSITIVE LOGITS
    urchase
    0.43
    ማሪ
    0.39
    מבר
    0.38
    なわ
    0.38
     Illinois
    0.37
    वों
    0.37
    渺
    0.37
    álás
    0.36
    INS
    0.36
     बिल
    0.36
    Activations Density 0.004%

    No Known Activations