© 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. 129706
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and names

    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
     Il
    0.51
     moat
    0.48
    pra
    0.46
     P
    0.45
    Pra
    0.45
     pra
    0.45
    Il
    0.45
     Pra
    0.43
    莫
    0.42
     PRA
    0.42
    POSITIVE LOGITS
     LOD
    0.47
    eslint
    0.43
     EMC
    0.42
    UNSIGNED
    0.41
     dodge
    0.41
     मनीष
    0.40
     Glossary
    0.39
     ফার
    0.38
    LAYER
    0.38
     Granite
    0.37
    Activations Density 0.001%

    No Known Activations