© 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. 205619
    Prev
    Next
    INDEX
    Explanations

    plaster and stucco textures

    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
    Negative Logits
    නේ
    0.52
     noget
    0.50
    ربی
    0.48
     atthakath
    0.46
    ܂
    0.46
     trimester
    0.46
     hipótesis
    0.46
     allError
    0.45
     햇
    0.45
     crebre
    0.45
    POSITIVE LOGITS
    ed
    0.48
     Sword
    0.47
    ED
    0.47
    D
    0.45
    Iss
    0.44
    ة
    0.44
    ex
    0.44
    éd
    0.43
    abled
    0.43
     вру
    0.43
    Activations Density 0.000%

    No Known Activations