© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235597
    Prev
    Next
    INDEX
    Explanations

    CSS transform: scale and translateY

    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_25_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
     Surely
    0.45
     Artifact
    0.40
    鐙
    0.39
     ALLOYS
    0.38
     Castell
    0.38
    鏤
    0.38
     Artis
    0.37
     Tours
    0.37
     Palabra
    0.37
    LAGAB
    0.36
    POSITIVE LOGITS
    ቭ
    0.43
    ząd
    0.41
     wellness
    0.37
    oč
    0.37
     cheque
    0.37
    āna
    0.36
    Ethereum
    0.36
     revoc
    0.36
     แอป
    0.36
    न्ग
    0.36
    Activations Density 0.001%

    No Known Activations