© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54935
    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_30_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
     बेटे
    0.44
     Tension
    0.41
     updates
    0.41
     czy
    0.39
     Updates
    0.39
     tension
    0.39
     Attack
    0.39
    讼
    0.39
     اول
    0.38
     Kald
    0.38
    POSITIVE LOGITS
    犧
    0.39
    రి
    0.36
    ôt
    0.35
     становништво
    0.33
    ỳ
    0.33
    стви
    0.33
     udrž
    0.33
    nico
    0.32
     रव
    0.32
    ıml
    0.32
    Activations Density 0.000%

    No Known Activations