© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14900
    Prev
    Next
    INDEX
    Explanations

    the debate and finances surrounding a specific state project (high speed rail).

    oai_token-act-pair · gemini-2.0-flash

    government projects and regulations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Government
    -1.09
     government
    -0.99
    Government
    -0.95
     GOVERNMENT
    -0.91
    government
    -0.88
     govt
    -0.82
    Govt
    -0.81
     Govt
    -0.80
    GOVERNMENT
    -0.76
    政府
    -0.64
    POSITIVE LOGITS
     betweenstory
    0.64
    RegistryLite
    0.62
    OGND
    0.61
    Geplaatst
    0.60
    fvar
    0.57
     ballot
    0.56
    abestanden
    0.55
     linkovi
    0.54
    rån
    0.54
    httphttps
    0.54
    Activations Density 6.181%

    No Known Activations