© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164937
    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_31_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
    flatten
    0.46
    монт
    0.45
    Flatten
    0.44
     ଜ
    0.40
     flattened
    0.39
     flatten
    0.38
    Bang
    0.37
     esclare
    0.37
    Bever
    0.36
     ፍ
    0.36
    POSITIVE LOGITS
     없이
    0.39
     PCA
    0.37
    INTERVAL
    0.37
     পাকসেন
    0.36
     qPCR
    0.36
     reapp
    0.36
     qRT
    0.36
    间隔
    0.35
     LiDAR
    0.35
     vector
    0.34
    Activations Density 0.000%

    No Known Activations