© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12679
    Prev
    Next
    INDEX
    Explanations

    words that are components of quoted speech or phrases that reference a specific place

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.66
     onResponse
    -0.63
     contextLoads
    -0.59
    PreferredItem
    -0.59
     ddelweddau
    -0.57
    
    -0.57
    SwingConstants
    -0.52
    posedge
    -0.50
    localctx
    -0.49
    styleType
    -0.48
    POSITIVE LOGITS
    Pyx
    0.53
    tlement
    0.52
     servire
    0.50
    ieke
    0.50
     übernehmen
    0.49
    ODES
    0.48
     pagare
    0.48
    зія
    0.47
    nija
    0.47
    odes
    0.46
    Activations Density 0.435%

    No Known Activations