© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15268
    Prev
    Next
    INDEX
    Explanations

    sneakers and trainers

    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_13_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
    paragus
    0.38
    Agr
    0.38
     clamp
    0.37
     embrace
    0.36
    |
    0.36
     writ
    0.36
    ния
    0.35
     agrarian
    0.35
    <unused60>
    0.35
    </h4>
    0.35
    POSITIVE LOGITS
    shoes
    0.51
     スニーカー
    0.50
    鞋
    0.49
     鞋
    0.43
     shoes
    0.43
     chaussures
    0.42
     sneakers
    0.42
     കലാ
    0.41
    clothes
    0.40
     direktor
    0.39
    Activations Density 0.014%

    No Known Activations