© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12934
    Prev
    Next
    INDEX
    Explanations

    Java GUI code relating to asynchronous task completion callbacks

    oai_token-act-pair · gemini-2.0-flash

    Interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    TypedDataSet
    -0.73
    IndentedString
    -0.69
    DeleteBehavior
    -0.60
    djangoproject
    -0.60
    thwaite
    -0.57
    WebElementEntity
    -0.56
    ckt
    -0.56
    Portale
    -0.56
    +#+#
    -0.54
    ConverterFactory
    -0.54
    POSITIVE LOGITS
    Referencies
    0.54
    ագրություններ
    0.50
     ViewController
    0.45
     Package
    0.45
     package
    0.44
    Lähteet
    0.43
    ავ
    0.42
     وتسجيلات
    0.42
    pexpr
    0.41
    InView
    0.41
    Activations Density 0.673%

    No Known Activations