© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2074
    Prev
    Next
    INDEX
    Explanations

    words relating to real estate, personal care workers and interior design or energy storage system

    oai_token-act-pair · gemini-2.0-flash

    home, property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     imageNamed
    -0.51
    amentul
    -0.50
     gostar
    -0.49
    CELONA
    -0.49
    SEGUIR
    -0.48
     Appell
    -0.47
     priori
    -0.47
    XmlAccessorType
    -0.47
    GRAFÍA
    -0.47
    ratory
    -0.46
    POSITIVE LOGITS
    المناصب
    0.73
     ModelExpression
    0.63
    SourceChecksum
    0.58
    FieldBuilder
    0.57
    Rohy
    0.57
    Климат
    0.54
    setViewportView
    0.54
     hypot
    0.54
    <bos>
    0.54
     متعلقه
    0.52
    Activations Density 1.268%

    No Known Activations