© 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. 11517
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and expressions

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    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
     property
    -0.45
     block
    -0.42
     dress
    -0.38
    klare
    -0.37
     性
    -0.37
    block
    -0.37
     ste
    -0.35
     views
    -0.35
     mindre
    -0.35
    性
    -0.35
    POSITIVE LOGITS
     propOrder
    0.90
    ьаж
    0.90
     AssemblyCulture
    0.86
    complexContent
    0.79
    UnknownFieldSet
    0.75
    يكب
    0.75
     ddelweddau
    0.73
     referenties
    0.72
     Italijani
    0.72
    homonymie
    0.67
    Activations Density 27.431%

    No Known Activations