© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176666
    Prev
    Next
    INDEX
    Explanations

    thread-safe

    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_20_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
    TECH
    0.46
     branded
    0.45
     used
    0.45
    aurus
    0.42
    ANS
    0.41
    orro
    0.41
    ă
    0.40
     safest
    0.40
    ವರೆ
    0.40
    感兴趣
    0.39
    POSITIVE LOGITS
     Youn
    0.44
     সাইফুদ্দিন
    0.44
     القيمه
    0.44
    }>\
    0.44
     Kamil
    0.44
    繆
    0.43
     penalty
    0.42
     implication
    0.41
    ρω
    0.41
     Dunne
    0.41
    Activations Density 0.000%

    No Known Activations