© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11982
    Prev
    Next
    INDEX
    Explanations

    words relating to illness, mental states, or medicine

    oai_token-act-pair · gemini-2.0-flash

    medical issues/attacks/sleep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     itſelf
    -0.98
     متعلقه
    -0.97
     myſelf
    -0.96
     مشين
    -0.94
    GEBURTSDATUM
    -0.94
    DockStyle
    -0.93
     themſelves
    -0.93
     propOrder
    -0.91
     Савезне
    -0.90
    writeFieldEnd
    -0.88
    POSITIVE LOGITS
    <
    0.44
     recorded
    0.42
    ()
    0.41
    нева
    0.41
     ak
    0.41
    <>
    0.41
     ses
    0.40
    iche
    0.40
     stra
    0.40
     happen
    0.39
    Activations Density 1.083%

    No Known Activations