© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5426
    Prev
    Next
    INDEX
    Explanations

    words related to scientific collaboration and analysis, particularly within a research context

    oai_token-act-pair · gemini-2.0-flash

    academic text

    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
    UnusedPrivate
    -0.73
    reportWebVitals
    -0.62
     arşivlendi
    -0.57
    setVerticalGroup
    -0.54
    HasForeignKey
    -0.52
    tagext
    -0.52
     ôm
    -0.50
    GenerationType
    -0.49
     scom
    -0.49
    XmlRootElement
    -0.49
    POSITIVE LOGITS
    webElementGuid
    0.60
    évaluateur
    0.54
     pinulongan
    0.52
    цездатний
    0.50
    ruptedException
    0.50
     NUKAT
    0.49
    javax
    0.47
    alous
    0.46
    )):
    0.46
    
    0.45
    Activations Density 2.168%

    No Known Activations