© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41136
    Prev
    Next
    INDEX
    Explanations

    years to retirement or doubling

    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_22_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
     dạy
    0.20
     integração
    0.20
    ગાહી
    0.20
    integrate
    0.19
     прогноз
    0.18
    ᾧ
    0.18
     playlists
    0.18
     previsão
    0.18
     Vect
    0.18
    𒁍
    0.18
    POSITIVE LOGITS
    рін
    0.18
    uten
    0.17
     thermal
    0.16
     Xuan
    0.16
    NEAPOLIS
    0.16
     removed
    0.16
    uties
    0.16
    Thermal
    0.16
    otre
    0.16
    ออก
    0.16
    Activations Density 0.015%

    No Known Activations