© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36987
    Prev
    Next
    INDEX
    Explanations

    Swedish

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     indigestion
    0.40
    addAlignment
    0.40
    alupe
    0.39
    الد
    0.38
    ignac
    0.38
     nipple
    0.37
     Valuation
    0.37
    燵
    0.37
    arlings
    0.37
     valuations
    0.36
    POSITIVE LOGITS
     S
    0.87
    <0xAF>
    0.74
     স
    0.66
     sett
    0.64
    S
    0.64
    স
    0.61
     الس
    0.59
     sätt
    0.55
     sette
    0.54
    𝑆
    0.54
    Activations Density 0.001%

    No Known Activations