© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168676
    Prev
    Next
    INDEX
    Explanations

    mild to moderate

    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_34_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
    ujian
    0.35
     disease
    0.35
     represents
    0.35
    ]<?
    0.34
    壊
    0.34
     తీవ్ర
    0.34
     severe
    0.33
     deadly
    0.33
     اللون
    0.33
    殞
    0.33
    POSITIVE LOGITS
     सही
    0.38
    WUE
    0.38
     NPTypeCode
    0.38
    เขียน
    0.38
     रक्षाबंधनाच्या
    0.38
    érences
    0.38
    东南
    0.38
     XY
    0.37
    最佳
    0.37
    ();
    0.37
    Activations Density 0.004%

    No Known Activations