© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235731
    Prev
    Next
    INDEX
    Explanations

    use

    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_25_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
    Sett
    0.37
    爺
    0.37
    وفة
    0.36
     脱
    0.36
    Euph
    0.35
     вну
    0.35
    Speakers
    0.34
     loyalty
    0.34
     settlements
    0.34
    astopol
    0.34
    POSITIVE LOGITS
    绣
    0.40
     Comp
    0.38
     Вме
    0.37
    重ね
    0.37
    ellido
    0.36
     جهان
    0.36
     주제
    0.36
    ประเทศไทย
    0.36
     وجدت
    0.35
     গবেষ
    0.35
    Activations Density 0.000%

    No Known Activations