© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212049
    Prev
    Next
    INDEX
    Explanations

    low-rank matrices

    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_20_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
    மிக
    0.45
     ነ
    0.44
     shoppers
    0.43
     送料
    0.41
     ጥ
    0.39
     sardines
    0.39
    छ
    0.39
    🗯
    0.39
    வியல்
    0.38
     굉장
    0.38
    POSITIVE LOGITS
    Pyrazole
    0.43
    AFTER
    0.42
     будут
    0.41
     Après
    0.41
     Andrés
    0.41
     haberse
    0.41
     после
    0.40
    ন্দ্ব
    0.40
    SERVER
    0.39
     COULD
    0.39
    Activations Density 0.003%

    No Known Activations