© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 259350
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    regation
    1.40
    
    1.40
     PGS
    1.35
    
    1.30
     Biblical
    1.30
    
    1.28
     deadly
    1.27
    
    1.26
     dredging
    1.25
     BCR
    1.25
    POSITIVE LOGITS
    ση
    1.12
     cex
    1.03
    have
    1.03
     accountable
    1.01
    är
    1.01
    ೋಜ
    1.00
     uud
    0.99
    setAlignment
    0.97
     extérieure
    0.97
    ो
    0.95
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.