© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4807
    Prev
    Next
    INDEX
    Explanations

    references to Donald Trump

    oai_token-act-pair · gemini-2.0-flash

    Trump

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GEBURTSDATUM
    -1.01
     }}"></
    -0.88
    NameInMap
    -0.82
     Por
    -0.78
     des
    -0.77
    EDEFAULT
    -0.77
     @"/
    -0.77
     Ber
    -0.69
     Se
    -0.69
     San
    -0.69
    POSITIVE LOGITS
     avoient
    1.60
     étoient
    1.57
     étoit
    1.48
     Monfieur
    1.45
     auroit
    1.45
     myſelf
    1.41
     abstrait
    1.34
     feroit
    1.34
     pleaſure
    1.34
     purpoſe
    1.31
    Activations Density 1.660%

    No Known Activations