© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219608
    Prev
    Next
    INDEX
    Explanations

    among

    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_47_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
    kich
    0.39
    reated
    0.38
    Wo
    0.38
    wo
    0.37
    тых
    0.37
     canary
    0.37
     বৃহত্তর
    0.37
    <unused2>
    0.36
    Preset
    0.36
    teki
    0.36
    POSITIVE LOGITS
    ܩ
    0.47
     POD
    0.38
     Wien
    0.36
     Donuts
    0.36
     taz
    0.36
     generalizes
    0.36
     የማ
    0.35
     금액
    0.35
    纍
    0.35
     核
    0.35
    Activations Density 0.000%

    No Known Activations