© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10173
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death, illness, and medical outcomes

    oai_token-act-pair · gemini-2.0-flash

    death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    DispatchToProps
    -0.85
    IVEREF
    -0.73
     typelib
    -0.69
    RenderAtEndOf
    -0.69
    GEBURTSDATUM
    -0.68
    WebVitals
    -0.67
    帖最后由
    -0.66
     handleMessage
    -0.66
    ConstraintMaker
    -0.66
    IonicModule
    -0.65
    POSITIVE LOGITS
     straight
    0.45
    おり
    0.43
    vertis
    0.41
    aka
    0.41
     hosted
    0.40
     STRA
    0.40
    ัจ
    0.40
     too
    0.40
    tování
    0.40
     ihop
    0.39
    Activations Density 1.326%

    No Known Activations