© 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. 9630
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to crime, legal proceedings, and courts

    oai_token-act-pair · gemini-2.0-flash

    legal charges

    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
    <bos>
    -0.86
     Cataloging
    -0.64
    elemField
    -0.61
    Personensuche
    -0.58
    Décès
    -0.57
    IntoConstraints
    -0.57
     CreateTagHelper
    -0.57
    Hochspringen
    -0.56
    EndInit
    -0.56
    initComponents
    -0.56
    POSITIVE LOGITS
     FetchType
    0.54
    ofür
    0.52
    Източници
    0.44
     Lijst
    0.42
    CURLOPT
    0.42
     Untold
    0.42
    ISupport
    0.42
    Options
    0.42
     precedence
    0.41
    odeon
    0.41
    Activations Density 4.546%

    No Known Activations