© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12489
    Prev
    Next
    INDEX
    Explanations

    words related to government committees and investigations

    oai_token-act-pair · gemini-2.0-flash

    Government officials

    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
     Washington
    -0.72
    TypedDataSet
    -0.70
    Washington
    -0.64
     washington
    -0.63
    ReusableCell
    -0.61
    StoryboardSegue
    -0.55
    washington
    -0.52
     فريبيس
    -0.52
     defaultstate
    -0.52
     WASHINGTON
    -0.50
    POSITIVE LOGITS
     House
    0.60
     Rep
    0.58
     Speaker
    0.56
    Speaker
    0.56
    Rep
    0.55
    Zeneca
    0.54
     speaker
    0.53
    shadowOffset
    0.51
     SPEAKER
    0.50
    House
    0.49
    Activations Density 10.846%

    No Known Activations