© 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. 12946
    Prev
    Next
    INDEX
    Explanations

    mentions of "primary care" or words indicating something is of primary importance

    oai_token-act-pair · gemini-2.0-flash

    primary

    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
     primary
    -1.42
     Primary
    -1.37
    Primary
    -1.34
    primary
    -1.31
    PRIMARY
    -1.23
     PRIMARY
    -1.15
     primaire
    -1.05
    Secondary
    -1.05
     Secondary
    -1.02
     secondary
    -1.01
    POSITIVE LOGITS
    RegistryLite
    0.56
    ArgsConstructor
    0.56
     miſ
    0.54
    клопе
    0.53
     Ră
    0.52
    awtextra
    0.52
    chartInstance
    0.52
     interstate
    0.51
    MigrationBuilder
    0.51
     ſte
    0.50
    Activations Density 9.903%

    No Known Activations