© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85407
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_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
    ذور
    0.45
     Herb
    0.44
    茎
    0.44
    جة
    0.44
     মূর্তি
    0.44
    抔
    0.43
    ፈ
    0.42
    ்க
    0.42
    ك
    0.42
    ُر
    0.41
    POSITIVE LOGITS
    arza
    0.61
     ایکسپریس
    0.51
    training
    0.49
    cpp
    0.48
    option
    0.46
     एक्सप्रेस
    0.45
    itsyn
    0.44
    directory
    0.44
    utility
    0.44
    '"
    0.42
    Activations Density 0.000%

    No Known Activations