© 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. 15309
    Prev
    Next
    INDEX
    Explanations

    Jamestown permanent English settlement

    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
     él
    0.43
     carr
    0.43
     drugs
    0.42
     nettoy
    0.41
     nettoyage
    0.40
    ুহ
    0.40
     lilies
    0.38
     us
    0.38
    ଼
    0.38
     weeds
    0.38
    POSITIVE LOGITS
    يت
    0.49
     ہزار
    0.48
    性别
    0.42
    ה
    0.41
     فقط
    0.40
    یه
    0.40
    یت
    0.40
    ية
    0.40
    בין
    0.40
     ছাড়াও
    0.39
    Activations Density 0.002%

    No Known Activations