© 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. 11850
    Prev
    Next
    INDEX
    Explanations

    references to hospitals, medical centers, and legal entities like corporations and insurance companies

    oai_token-act-pair · gemini-2.0-flash

    Hospital

    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
     ROOMS
    -0.43
     FormData
    -0.42
     travellers
    -0.42
     digitais
    -0.41
     بيها
    -0.41
     diría
    -0.41
     enamorado
    -0.40
     traveller
    -0.40
    Deaths
    -0.40
     travelers
    -0.40
    POSITIVE LOGITS
    ArgsConstructor
    0.96
    IBOutlet
    0.89
    AsUp
    0.87
    __':
    0.77
     AssemblyTitle
    0.77
    ItemBackground
    0.75
    __":
    0.74
    QMetaType
    0.74
    LookAnd
    0.74
     estekak
    0.73
    Activations Density 1.442%

    No Known Activations