© 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. 11171
    Prev
    Next
    INDEX
    Explanations

    words that are repeated with emphasis, along with related concept words

    oai_token-act-pair · gemini-2.0-flash

    Repeated words

    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
    webElementXpaths
    -0.78
    gameserver
    -0.73
    RegressionTest
    -0.66
    styleType
    -0.63
     nahilalakip
    -0.58
    NameInMap
    -0.57
    oredCriteria
    -0.56
    دانشنامهٔ
    -0.54
    RTSC
    -0.52
    UnknownFieldSet
    -0.52
    POSITIVE LOGITS
    loem
    0.61
    endphp
    0.60
     PhpStorm
    0.55
    XmlRootElement
    0.54
    HtmlAttribute
    0.51
     inspir
    0.49
     Casualty
    0.49
     soigne
    0.48
    Winds
    0.48
     oubli
    0.48
    Activations Density 27.125%

    No Known Activations