© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 177
    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_2_width_16k_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
    ᄊ
    0.98
    ate
    0.96
    ation
    0.96
    ь
    0.92
    <0x80>
    0.91
    ('.')[
    0.87
    ं
    0.85
    ьте
    0.82
    ungeons
    0.82
                            
    0.81
    POSITIVE LOGITS
     ópt
    1.01
    னர்
    1.01
    лів
    0.93
    в
    0.93
     aí
    0.92
    ಗಾರ
    0.90
     виды
    0.86
    fully
    0.86
    ყოფ
    0.85
    es
    0.84
    Activations Density 0.277%

    No Known Activations