© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2369
    Prev
    Next
    INDEX
    Explanations

    words related to negative outcomes, threats, conflict, or danger

    oai_token-act-pair · gemini-2.0-flash

    threat

    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
     threat
    -2.19
     Threat
    -1.97
    threat
    -1.92
    Threat
    -1.92
     threats
    -1.91
     Threats
    -1.77
     threatening
    -1.72
     threaten
    -1.62
     threatened
    -1.61
    Threats
    -1.56
    POSITIVE LOGITS
    unknownFields
    0.64
    IonicModule
    0.59
    DeleteBehavior
    0.58
    MessageTagHelper
    0.57
    CloseOperation
    0.54
    HasForeignKey
    0.52
    Nationalité
    0.50
    ссмо
    0.47
     âgées
    0.47
     unwritten
    0.47
    Activations Density 3.781%

    No Known Activations