© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198118
    Prev
    Next
    INDEX
    Explanations

    water connections, plumbing, steam, flushing

    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_12_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
    ates
    0.24
     urinary
    0.23
     bladder
    0.23
     Twitch
    0.22
    حة
    0.21
     glomerular
    0.21
    /
    0.21
     Doyle
    0.21
    ployment
    0.21
     Bowser
    0.21
    POSITIVE LOGITS
     lidí
    0.26
     सुरू
    0.24
     루트
    0.24
    山的
    0.24
    cv
    0.23
     лечения
    0.23
     empezamos
    0.23
    pubescens
    0.22
    墂
    0.22
    靜
    0.22
    Activations Density 0.000%

    No Known Activations