© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2322
    Prev
    Next
    INDEX
    Explanations

    words related to computers, especially laptops, and their components or modification.

    oai_token-act-pair · gemini-2.0-flash

    Computers and phones

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    허
    -0.66
     Penh
    -0.62
    XmlType
    -0.62
     fieldNum
    -0.61
     poffe
    -0.60
    uxxxx
    -0.59
    DebuggerNonUser
    -0.59
    rawDesc
    -0.57
    脚注の使い方
    -0.56
    haustible
    -0.56
    POSITIVE LOGITS
    #__
    0.54
     المعيارى
    0.53
     незавершена
    0.50
     Phone
    0.49
    runApp
    0.48
    makeText
    0.46
     Pre
    0.44
     pré
    0.42
    OGND
    0.42
    int
    0.41
    Activations Density 1.792%

    No Known Activations