© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37017
    Prev
    Next
    INDEX
    Explanations

    descriptive characteristics

    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_50_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
    臨
    0.44
    道的
    0.41
     Dali
    0.40
    Flash
    0.39
    Dal
    0.39
    iling
    0.39
    Dale
    0.38
    ForItem
    0.38
    邓
    0.38
    lage
    0.37
    POSITIVE LOGITS
    觀
    0.47
    玄
    0.46
    观
    0.44
     Xuan
    0.43
     Xeon
    0.42
     quan
    0.39
    creens
    0.39
     createNative
    0.38
     domine
    0.37
    생
    0.36
    Activations Density 0.008%

    No Known Activations