© 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. 14831
    Prev
    Next
    INDEX
    Explanations

    legal documents and references to court proceedings

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    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
     BOSTON
    -1.14
     SANTA
    -1.11
     CHICAGO
    -1.10
     MARIE
    -1.09
     SYDNEY
    -1.09
     PHILADELPHIA
    -1.06
     COLORADO
    -1.04
     BERLIN
    -1.03
     AUSTIN
    -1.01
     WAYNE
    -1.01
    POSITIVE LOGITS
     IS
    1.10
     AS
    0.96
     E
    0.90
     AT
    0.88
     D
    0.86
    ES
    0.86
     IT
    0.86
     G
    0.85
     B
    0.84
    IS
    0.82
    Activations Density 0.741%

    No Known Activations