© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260152
    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
    ر
    1.15
    ation
    1.08
     dei
    1.07
    お
    1.06
    
    0.97
    x
    0.94
    attice
    0.94
     neutrality
    0.94
    സ്
    0.92
    г
    0.91
    POSITIVE LOGITS
    禧
    1.37
    艿
    1.31
    να
    1.31
    eaa
    1.29
    殑
    1.26
    मिल
    1.26
    ی
    1.24
    eils
    1.23
     rigidly
    1.22
    llo
    1.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.