© 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. 219122
    Prev
    Next
    INDEX
    Explanations

    Dok

    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
    1
    0.71
    Press
    0.52
     arch
    0.49
     Press
    0.48
    বার্গ
    0.48
     manager
    0.48
     staff
    0.47
     out
    0.46
     beverage
    0.46
     Quick
    0.46
    POSITIVE LOGITS
    عليه
    0.50
    椙
    0.50
    𝒋
    0.48
    単純
    0.47
    难道
    0.47
     ordena
    0.46
    微分
    0.46
    љашње
    0.46
    ്യത
    0.46
    ើន
    0.46
    Activations Density 0.000%

    No Known Activations