© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133833
    Prev
    Next
    INDEX
    Explanations

    parenteral or central infusion/catheter

    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_37_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
    ռ
    0.44
     lounges
    0.42
     առ
    0.42
     לג
    0.39
     fascia
    0.38
    ゐ
    0.37
     lounge
    0.36
    第一題
    0.36
    探测
    0.36
    旸
    0.36
    POSITIVE LOGITS
    中央
    0.50
     central
    0.47
     admixture
    0.47
     infusion
    0.47
     Paren
    0.46
    Central
    0.44
     Injection
    0.44
    paren
    0.44
     центра
    0.44
     centrales
    0.44
    Activations Density 0.001%

    No Known Activations