© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81640
    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_0_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
    ுக்
    0.54
    恵
    0.50
    lc
    0.46
    觀
    0.46
     défendre
    0.46
     bays
    0.45
    но
    0.45
     usl
    0.44
    िस
    0.44
    élect
    0.44
    POSITIVE LOGITS
     Wurzel
    0.49
    ]
    0.49
     cathode
    0.46
    ;
    0.46
     Really
    0.44
    countery
    0.44
     Futuristic
    0.44
    nger
    0.44
     Kaya
    0.43
     perist
    0.43
    Activations Density 0.000%

    No Known Activations