© 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. 10107
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry, polymers, and organic chemistry compounds

    oai_token-act-pair · gemini-2.0-flash

    chemical compounds and structures

    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
     '\\;'
    -0.60
    AlterField
    -0.58
     betweenstory
    -0.53
    ValueStyle
    -0.50
    setVerticalGroup
    -0.50
     légale
    -0.48
    WebElementEntity
    -0.48
     tenue
    -0.47
     Nell
    -0.46
     Dreamer
    -0.45
    POSITIVE LOGITS
    TargetException
    0.75
    djangoproject
    0.61
    IMPORTED
    0.55
     ddelweddau
    0.55
    notifyListeners
    0.54
    guint
    0.54
    Pautan
    0.53
    Amicalement
    0.53
    licability
    0.53
     réessayer
    0.53
    Activations Density 3.600%

    No Known Activations