© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136161
    Prev
    Next
    INDEX
    Explanations

    white flowers

    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_12_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
    Safari
    0.17
     rohkem
    0.17
    あります
    0.17
    сү
    0.16
     sơn
    0.16
     ومرحبا
    0.16
    1
    0.16
    Thi
    0.16
     beginners
    0.16
     मिळते
    0.16
    POSITIVE LOGITS
    ’
    0.18
     MILLER
    0.17
    '
    0.17
     Miller
    0.17
     પ્રમાણે
    0.17
     Calder
    0.17
     apag
    0.16
     dole
    0.16
    apin
    0.15
     לפי
    0.15
    Activations Density 0.000%

    No Known Activations