© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83895
    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_23_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
    тесь
    0.52
    गढ़
    0.47
    आईओएस
    0.46
    尸
    0.45
    𝑈
    0.44
     Identifier
    0.44
    गढ़
    0.43
    नियों
    0.42
     行っ
    0.42
     Nin
    0.42
    POSITIVE LOGITS
    č
    0.58
    al
    0.49
    Circ
    0.47
    ad
    0.46
    ink
    0.46
    点
    0.46
    Canadian
    0.45
    arlama
    0.44
    é
    0.44
    т
    0.42
    Activations Density 0.000%

    No Known Activations