© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13076
    Prev
    Next
    INDEX
    Explanations

    terms related to law, government, and civic administration

    oai_token-act-pair · gemini-2.0-flash

    United States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     EEUU
    -0.76
    Diweddarwch
    -0.72
    protoimpl
    -0.71
    amerikanischer
    -0.70
    ();)
    -0.69
    cticut
    -0.69
    parsedMessage
    -0.66
     USAF
    -0.66
     raiſ
    -0.65
    $}}
    -0.65
    POSITIVE LOGITS
    -
    0.45
     money
    0.44
    ädchen
    0.43
    viewDidLoad
    0.42
     通販
    0.41
     
    0.40
    enerbahçe
    0.40
     national
    0.40
     bio
    0.40
    ESTY
    0.40
    Activations Density 9.798%

    No Known Activations