© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11402
    Prev
    Next
    INDEX
    Explanations

    names of people, companies and institutions

    oai_token-act-pair · gemini-2.0-flash

    business and professional contexts

    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
    writeField
    -0.78
     nonatomic
    -0.67
     OFDb
    -0.66
    MockBean
    -0.64
    Rohy
    -0.60
     autorytatywna
    -0.59
    XmlAccessType
    -0.58
    #+#
    -0.58
    EndGlobalSection
    -0.56
     Biôgrafia
    -0.56
    POSITIVE LOGITS
    +:+
    0.58
    ıştı
    0.48
    圣节
    0.44
     Märchen
    0.44
     évêque
    0.43
    ieteur
    0.43
     ferrovia
    0.43
    反対
    0.43
     témoin
    0.43
     Jérusalem
    0.43
    Activations Density 8.693%

    No Known Activations