© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7410
    Prev
    Next
    INDEX
    Explanations

    publishing and publication

    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_39_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
    σεις
    0.38
    ⿱
    0.38
    COX
    0.38
    ัจ
    0.36
    odyne
    0.36
    conjug
    0.36
     Vis
    0.35
    讴
    0.35
     conjug
    0.35
     encountered
    0.35
    POSITIVE LOGITS
     fruct
    0.42
     pept
    0.40
     رئیس
    0.39
     pickups
    0.38
    rophe
    0.37
    date
    0.36
    Pickup
    0.36
     स्टेप
    0.35
    polis
    0.35
     હાઉસ
    0.35
    Activations Density 0.003%

    No Known Activations