© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174855
    Prev
    Next
    INDEX
    Explanations

    dropout probability parameter

    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_24_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
    seller
    0.43
    är
    0.38
     ভারতীয়
    0.38
    establishment
    0.37
    農
    0.37
    container
    0.37
     가정
    0.37
    overflow
    0.36
    𝖑
    0.36
    രംഭ
    0.36
    POSITIVE LOGITS
     امی
    0.39
     Simons
    0.39
     IRA
    0.38
    ORDAN
    0.38
     меж
    0.38
     secondly
    0.37
    INED
    0.37
     বল
    0.36
     билан
    0.36
    ³.
    0.36
    Activations Density 0.002%

    No Known Activations