© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54964
    Prev
    Next
    INDEX
    Explanations

    introduced

    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_30_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
    unteer
    0.40
     refraction
    0.40
    readystate
    0.39
    🦵
    0.38
     turista
    0.38
    ﹗
    0.38
     solvent
    0.38
    🥰
    0.38
     antir
    0.37
    燿
    0.37
    POSITIVE LOGITS
    Obama
    0.57
     Obama
    0.53
     Mindfulness
    0.51
     २०१
    0.50
     smartphone
    0.49
     Smartphones
    0.48
    smartphone
    0.48
     smartphones
    0.47
     Smartphone
    0.45
    スマホ
    0.45
    Activations Density 0.027%

    No Known Activations