© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9868
    Prev
    Next
    INDEX
    Explanations

    words related to law and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    legal terminology and procedural terms

    np_token-act-pair-logits · gpt-4o-mini

    legal jurisdiction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     bezeichneter
    -0.56
    Filmografia
    -0.54
    featureID
    -0.54
     solicitors
    -0.52
     Deliber
    -0.52
     Rossini
    -0.50
    Demografia
    -0.49
     företag
    -0.49
    Autoritní
    -0.49
    msgSender
    -0.48
    POSITIVE LOGITS
     MainAxisSize
    0.55
    TestTools
    0.48
    expandindo
    0.46
    partements
    0.46
    мента
    0.46
    Password
    0.45
    pilar
    0.45
     wall
    0.45
    gdala
    0.44
    wall
    0.44
    Activations Density 4.358%

    No Known Activations