© 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. 201144
    Prev
    Next
    INDEX
    Explanations

    say "-"

    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
     カル
    0.45
    界
    0.40
    慶
    0.38
     Cal
    0.37
    ACTER
    0.37
    opically
    0.37
    求解
    0.37
     пов
    0.36
    سون
    0.36
    荡
    0.36
    POSITIVE LOGITS
    income
    0.65
     Income
    0.64
     income
    0.64
    Income
    0.58
     INCOME
    0.58
    -,
    0.53
    -/
    0.52
    收入
    0.50
     इनकम
    0.49
    case
    0.42
    Activations Density 0.001%

    No Known Activations