© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48250
    Prev
    Next
    INDEX
    Explanations

    enjoy long-lasting benefits

    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_31_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
    स्करण
    0.41
    詐
    0.40
    ୌ
    0.38
     upholstery
    0.38
    fraud
    0.38
     básico
    0.37
    そのまま
    0.37
     свою
    0.37
    淪
    0.36
     другую
    0.36
    POSITIVE LOGITS
     huge
    0.40
    lidir
    0.40
    huge
    0.38
     luoghi
    0.38
    benefits
    0.38
     random
    0.36
     congrat
    0.36
    random
    0.35
     beneficios
    0.35
     underpinned
    0.35
    Activations Density 0.004%

    No Known Activations