© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205771
    Prev
    Next
    INDEX
    Explanations

    multiples of 3

    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_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Unidos
    0.18
     puisse
    0.18
    etaan
    0.17
    taro
    0.17
     classmate
    0.16
    𝕝
    0.16
     cruz
    0.16
    arro
    0.16
    ándolo
    0.16
    лому
    0.16
    POSITIVE LOGITS
    ოლ
    0.18
     only
    0.16
     Lis
    0.15
    引
    0.15
     Lose
    0.15
     haired
    0.15
     Conversely
    0.15
    ﺎ
    0.15
    プレイヤー
    0.15
    මාණ
    0.15
    Activations Density 0.007%

    No Known Activations