© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203676
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ຢ່າງ
    0.43
    อย่าง
    0.42
     chỉ
    0.40
     seulement
    0.40
     clairement
    0.39
     ins
    0.38
     apenas
    0.36
    lardır
    0.35
     о
    0.35
     only
    0.35
    POSITIVE LOGITS
     time
    0.57
    时间
    0.55
    时间内
    0.55
     времени
    0.55
     tiempo
    0.54
    Time
    0.54
     시간을
    0.54
     czas
    0.52
     الوقت
    0.52
    AndTime
    0.52
    Activations Density 0.000%

    No Known Activations