© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 84032
    Prev
    Next
    INDEX
    Explanations

    your recipient

    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_29_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
     unaffected
    0.31
     ላ
    0.31
    ได้รับการ
    0.29
    therefore
    0.29
     выз
    0.29
     લાગે
    0.28
    ंता
    0.28
    !()
    0.28
    EventListeners
    0.28
    ể
    0.28
    POSITIVE LOGITS
     thrust
    0.32
    木の
    0.29
     masked
    0.29
     nears
    0.29
     accompan
    0.29
     Range
    0.29
     self
    0.28
     surprising
    0.28
     WHILE
    0.28
    thrust
    0.27
    Activations Density 0.027%

    No Known Activations