© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33730
    Prev
    Next
    INDEX
    Explanations

    range(1,

    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_40_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
    ಕ್ತ
    0.34
     क्ला
    0.33
    മൂ
    0.32
     QRCode
    0.32
     Batista
    0.32
     Anaheim
    0.32
    巴士
    0.32
    灘
    0.32
    SpringBoot
    0.31
     buses
    0.31
    POSITIVE LOGITS
    icación
    0.38
    achio
    0.37
    PHONY
    0.36
     Coefficients
    0.36
    hém
    0.36
    ciaux
    0.36
    bolos
    0.36
    ALTERNATIVNAMEN
    0.36
    icação
    0.35
     管理
    0.34
    Activations Density 0.001%

    No Known Activations