© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 219102
    Prev
    Next
    INDEX
    Explanations

    younger age

    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_16_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
    ’
    0.61
    rels
    0.60
    ।
    0.48
    apon
    0.46
    uts
    0.46
    eke
    0.45
    .’
    0.45
    etted
    0.45
    icked
    0.45
    ”
    0.45
    POSITIVE LOGITS
    ס
    0.52
     prosec
    0.50
     debes
    0.49
    если
    0.49
     conflic
    0.48
    ियों
    0.47
    чете
    0.47
     merasa
    0.47
    ский
    0.47
     объем
    0.47
    Activations Density 0.000%

    No Known Activations