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

    Neuronpedia

    Jacobian LensNEW
    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. 50573
    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
     असा
    0.36
     genital
    0.36
    ૉ
    0.35
     Topological
    0.35
     denars
    0.35
    oscale
    0.34
    ู่
    0.34
    ränkt
    0.33
     Komis
    0.33
     ("[
    0.33
    POSITIVE LOGITS
    >{
    0.39
    Monday
    0.38
    Press
    0.38
     collapse
    0.37
     sacked
    0.37
     Ling
    0.36
    try
    0.36
     শুনেছি
    0.36
    蚣
    0.35
    Aber
    0.35
    Activations Density 0.000%

    No Known Activations