© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121782
    Prev
    Next
    INDEX
    Explanations

    state updates in code

    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_27_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
    ゚
    0.42
     meetup
    0.37
     punk
    0.37
    ያንዳንዱ
    0.36
    뵙
    0.36
     repair
    0.35
     Drs
    0.35
     everybody
    0.35
    Punk
    0.35
     دیکھیں
    0.35
    POSITIVE LOGITS
     ભાર
    0.39
    itaires
    0.38
     участи
    0.37
     நூற்ற
    0.37
     затра
    0.36
    SERIAL
    0.36
    刃
    0.36
     привле
    0.35
    บร
    0.35
    turning
    0.34
    Activations Density 0.000%

    No Known Activations