© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51293
    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
    Not in Any Lists

    No Comments

    Negative Logits
    othe
    0.54
    ގައި
    0.54
    य
    0.53
    ये
    0.51
    加え
    0.50
    йо
    0.49
    ಥ
    0.49
    ಯ
    0.49
    other
    0.49
     dejando
    0.48
    POSITIVE LOGITS
    0.47
     scout
    0.47
     scouts
    0.47
     moor
    0.46
     sack
    0.45
     ross
    0.45
     score
    0.45
     championship
    0.45
     conform
    0.44
     tls
    0.42
    Activations Density 0.000%

    No Known Activations