© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219404
    Prev
    Next
    INDEX
    Explanations

    Karl

    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_47_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
    ]){
    0.38
     gitt
    0.37
     gud
    0.37
    WEIGHT
    0.36
     Punj
    0.34
     вер
    0.34
    斯拉
    0.34
    rzeb
    0.33
    ̙
    0.33
    䒾
    0.33
    POSITIVE LOGITS
    Emergency
    0.41
     Emerg
    0.40
    aminan
    0.39
    팔
    0.39
    atoms
    0.38
     Emergency
    0.38
     फॉ
    0.38
    Zak
    0.38
    метка
    0.37
     فرش
    0.37
    Activations Density 0.000%

    No Known Activations