© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 37042
    Prev
    Next
    INDEX
    Explanations

    bubbles and boiling

    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_31_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
     CIT
    0.37
     gostar
    0.36
     unoccupied
    0.35
     科
    0.35
     torn
    0.34
     JI
    0.34
    thisobject
    0.34
     vaccinated
    0.34
     vacant
    0.34
    órios
    0.34
    POSITIVE LOGITS
    bubble
    0.47
    bubbles
    0.46
    itches
    0.45
     lex
    0.39
    localization
    0.39
     Bubble
    0.39
    笕
    0.39
    lex
    0.38
    observations
    0.38
     bubbles
    0.38
    Activations Density 0.006%

    No Known Activations