© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10012
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to thoughts, intentions, statistics, authorship, and inventions

    oai_token-act-pair · gemini-2.0-flash

    People and their actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    rrggbb
    -0.75
     financières
    -0.73
    TagMode
    -0.73
    endphp
    -0.71
     vectorielles
    -0.64
     médicaux
    -0.64
     विश्वसनीयता
    -0.64
     moschino
    -0.64
     économiques
    -0.63
     religieuses
    -0.63
    POSITIVE LOGITS
     does
    1.13
     says
    1.05
     wants
    0.98
     Does
    0.94
     knows
    0.92
    does
    0.92
     believes
    0.92
     recommends
    0.90
    Does
    0.89
     asks
    0.89
    Activations Density 3.035%

    No Known Activations