© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143679
    Prev
    Next
    INDEX
    Explanations

    classic, traditional

    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_46_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
    Imagen
    0.43
     мати
    0.42
    ierna
    0.40
     الوح
    0.39
     gathered
    0.39
    licz
    0.38
    Xiv
    0.38
    ier
    0.38
     vignettes
    0.37
    ]+
    0.36
    POSITIVE LOGITS
     classic
    0.48
    classic
    0.47
    经典的
    0.46
    पादन
    0.44
     tradisional
    0.43
     klasik
    0.43
    经典
    0.42
     klassischen
    0.42
     Classic
    0.41
    是中国
    0.41
    Activations Density 0.000%

    No Known Activations