© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11135
    Prev
    Next
    INDEX
    Explanations

    mentions of business markets in news or fiction

    oai_token-act-pair · gemini-2.0-flash

    giant

    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
    DockStyle
    -0.80
    DeleteBehavior
    -0.77
    ImageContext
    -0.73
     AssemblyVersion
    -0.68
    MigrationBuilder
    -0.67
    InjectAttribute
    -0.65
    省市镇
    -0.65
    QMetaType
    -0.63
    FontOfSize
    -0.61
    InSection
    -0.59
    POSITIVE LOGITS
    twimg
    0.62
    IVEN
    0.55
    󠁿
    0.54
    ⓧ
    0.52
     invid
    0.52
    Gave
    0.52
    endpush
    0.52
    illiers
    0.51
    ttemberg
    0.51
    pyplot
    0.51
    Activations Density 6.742%

    No Known Activations