© 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. 217546
    Prev
    Next
    INDEX
    Explanations

    phonetic parts

    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
     BAY
    0.54
    BAY
    0.53
     Bay
    0.51
     bay
    0.51
    Bay
    0.48
    ベイ
    0.46
    bay
    0.46
     Uy
    0.45
    Uy
    0.42
     K
    0.42
    POSITIVE LOGITS
     hu
    0.45
    hatt
    0.41
    binom
    0.41
     Bel
    0.41
    bu
    0.41
     अपर
    0.40
     Bu
    0.40
     దో
    0.40
    rä
    0.39
    Hu
    0.39
    Activations Density 0.008%

    No Known Activations