© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40761
    Prev
    Next
    INDEX
    Explanations

    Coca-Cola and diet soda

    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_3_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
     is
    0.77
    คุณ
    0.66
     society
    0.62
     społec
    0.62
    luğu
    0.61
    l
    0.61
     bệnh
    0.59
     stessi
    0.59
     cheveux
    0.59
    dye
    0.59
    POSITIVE LOGITS
    ي
    0.80
    )،
    0.78
    _
    0.75
    (
    0.75
    ి
    0.74
    It
    0.71
    ),
    0.70
    )
    0.69
    ام
    0.69
    ()),
    0.69
    Activations Density 0.000%

    No Known Activations