© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 133
    Prev
    Next
    INDEX
    Explanations

    alpha-numeric code from software and network protocols

    oai_token-act-pair · gemini-2.0-flash

    Code and DDT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     betweenstory
    -0.51
     Roskov
    -0.41
    olella
    -0.39
    PerformLayout
    -0.39
    delwed
    -0.38
     kasarigan
    -0.38
    memoized
    -0.37
    ArrowToggle
    -0.37
    Local
    -0.36
     (‘
    -0.35
    POSITIVE LOGITS
    stdc
    0.75
    TagMode
    0.74
    WebVitals
    0.69
    makeConstraints
    0.68
    Espèce
    0.66
    неопр
    0.66
    etheless
    0.65
    bootstrapcdn
    0.65
    ChildScrollView
    0.63
     BoxDecoration
    0.61
    Activations Density 18.943%

    No Known Activations