© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101462
    Prev
    Next
    INDEX
    Explanations

    bacterial diseases

    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_44_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
    费
    0.37
    嘖
    0.37
    セレ
    0.37
    十九
    0.36
    TorpedoStore
    0.35
     xix
    0.35
    chol
    0.34
    카
    0.34
    ❖
    0.34
    rations
    0.34
    POSITIVE LOGITS
    艮
    0.42
    仡
    0.42
     Gallo
    0.40
    ன்னு
    0.40
     کامیابی
    0.39
    onTouch
    0.39
     anime
    0.38
     Qg
    0.38
    ယောက်
    0.38
    tou
    0.36
    Activations Density 0.001%

    No Known Activations