© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10997
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibility or obligation

    oai_token-act-pair · gemini-2.0-flash

    legal/system responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    
    -0.96
     متعلقه
    -0.89
     Wiktionnaire
    -0.82
    GEBURTSDATUM
    -0.78
    Rhestr
    -0.75
     виправивши
    -0.75
    rrggbb
    -0.75
    ThroughAttribute
    -0.74
    RectangleBorder
    -0.73
    rungsseite
    -0.73
    POSITIVE LOGITS
    <bos>
    0.54
     &[
    0.46
    Web
    0.46
    isseaux
    0.45
     who
    0.44
     Nutella
    0.44
    ंदीखरीदारी
    0.44
    web
    0.43
     Brust
    0.43
     Ellos
    0.42
    Activations Density 0.610%

    No Known Activations