© 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. 212020
    Prev
    Next
    INDEX
    Explanations

    muted colors and earth tones

    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
     nois
    0.43
     escul
    0.43
     semula
    0.42
    점으로
    0.42
    猛
    0.42
     fierce
    0.42
     hardening
    0.41
     plantar
    0.41
    ammation
    0.41
     suspicious
    0.41
    POSITIVE LOGITS
    nati
    0.46
    ಿಸಿದ್ದಾರೆ
    0.43
    ;.
    0.42
    uvre
    0.41
    utives
    0.41
    ATIVES
    0.41
    ższy
    0.41
     革
    0.41
     आश्रम
    0.41
    qués
    0.41
    Activations Density 0.003%

    No Known Activations