© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    numbers, dollar signs, and words related to money

    oai_token-act-pair · gemini-2.0-flash

    Numerical values; money

    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
     متعلقه
    -0.75
    DockStyle
    -0.74
    Diwedd
    -0.69
     gyhoeddwyd
    -0.68
    UserScript
    -0.67
     protoimpl
    -0.64
    setVerticalGroup
    -0.63
    RenderAtEndOf
    -0.63
    verwijspagina
    -0.61
    enumi
    -0.59
    POSITIVE LOGITS
     Equipo
    0.54
     ufe
    0.50
    IntoConstraints
    0.47
    Canton
    0.47
    IInterface
    0.46
    sibilities
    0.46
     leſs
    0.45
     Specialization
    0.45
    SpringBootTest
    0.44
     verba
    0.43
    Activations Density 4.027%

    No Known Activations