© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237168
    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_46_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
     D
    0.52
    렐
    0.46
    MIL
    0.41
     Д
    0.40
     Delaware
    0.40
     الد
    0.39
    𝑫
    0.38
    millis
    0.38
    𝐃
    0.38
    項目
    0.37
    POSITIVE LOGITS
     permutations
    0.44
    ضاء
    0.40
    λεσ
    0.40
     Loki
    0.39
    定番
    0.39
     कंपाउंड
    0.39
     bajos
    0.39
     COMPO
    0.38
    ั้ง
    0.38
     detox
    0.37
    Activations Density 0.000%

    No Known Activations