© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76836
    Prev
    Next
    INDEX
    Explanations

    comma

    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_53_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
     न्यूज़
    0.40
    蝣
    0.40
    ágenes
    0.38
    ADOS
    0.38
    ුවන්
    0.38
    磁盘
    0.36
    绘制
    0.36
     zemlji
    0.36
    一般的な
    0.35
    骼
    0.35
    POSITIVE LOGITS
    laut
    0.37
    uto
    0.36
     Schmitt
    0.34
     interação
    0.34
    ތ
    0.34
    etzt
    0.33
     Kn
    0.33
     Sear
    0.33
     Vis
    0.33
     Sensor
    0.33
    Activations Density 0.014%

    No Known Activations