© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7350
    Prev
    Next
    INDEX
    Explanations

    words associated with government agencies, national security, armed forces, and research

    oai_token-act-pair · gemini-2.0-flash

    organized entities

    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
    Negative Logits
    protoimpl
    -0.72
     levure
    -0.68
    脚注の使い方
    -0.68
    hlands
    -0.65
    seamnă
    -0.63
    Conception
    -0.63
    décoration
    -0.58
     sacré
    -0.57
     ModelRenderer
    -0.57
     médaille
    -0.57
    POSITIVE LOGITS
     force
    0.60
     presence
    0.52
     effort
    0.51
     sm
    0.48
     EFF
    0.48
    HttpDelete
    0.47
     capabilities
    0.47
     footprint
    0.47
    Force
    0.46
    Atoi
    0.46
    Activations Density 4.280%

    No Known Activations