© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4029
    Prev
    Next
    INDEX
    Explanations

    'as is' or 'as'

    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_40_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
    ätzung
    0.39
     Ulm
    0.34
    bea
    0.34
    боры
    0.34
    ディング
    0.34
     para
    0.33
    ادات
    0.33
     Stub
    0.33
    heber
    0.33
    颢
    0.33
    POSITIVE LOGITS
     as
    1.50
     As
    1.33
    As
    1.23
     كما
    1.12
     както
    1.06
    そのまま
    1.02
     AS
    1.01
     sebagaimana
    0.96
     그대로
    0.94
    as
    0.89
    Activations Density 0.287%

    No Known Activations