© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12493
    Prev
    Next
    INDEX
    Explanations

    Java-related code and error messages.

    oai_token-act-pair · gemini-2.0-flash

    lang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    UpInside
    -0.96
    ollectionView
    -0.92
     disponibilités
    -0.88
    ViewFeatures
    -0.81
    EndContext
    -0.80
    onViewCreated
    -0.79
    Obrázky
    -0.79
     pylint
    -0.76
     nakalista
    -0.76
    RoutingModule
    -0.76
    POSITIVE LOGITS
    <bos>
    0.79
    class
    0.50
    bin
    0.45
    '
    0.42
    -
    0.41
    idopsis
    0.41
    тря
    0.40
    Play
    0.40
    top
    0.40
    Session
    0.39
    Activations Density 3.208%

    No Known Activations