© 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. 195011
    Prev
    Next
    INDEX
    Explanations

    call bells

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Doing
    0.99
     Doing
    0.97
     doing
    0.94
    doing
    0.86
     do
    0.63
     melakukan
    0.63
    做
    0.61
    ทำ
    0.58
    Do
    0.57
    do
    0.56
    POSITIVE LOGITS
     cap
    0.38
    堰
    0.38
     צו
    0.37
    Օ
    0.36
     kapp
    0.36
    坫
    0.35
     Crafts
    0.35
     MAGAZ
    0.34
     Caps
    0.34
     ఉంట
    0.34
    Activations Density 0.002%

    No Known Activations