© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3793
    Prev
    Next
    INDEX
    Explanations

    lines of code that are import statements in Java, where there is a series of period-separated names

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    [];
    -0.49
    ored
    -0.48
    ressee
    -0.47
    ItemName
    -0.47
     Agrico
    -0.47
     aching
    -0.46
     bruised
    -0.46
    .*")]
    -0.46
    CharCode
    -0.46
    PostalCode
    -0.45
    POSITIVE LOGITS
    UnusedPrivate
    0.98
    WebServlet
    0.91
    XmlAccessType
    0.88
    bootstrapcdn
    0.87
    parsedMessage
    0.85
    invokeLater
    0.82
    mybatisplus
    0.81
    stateProvider
    0.80
     resourceCulture
    0.80
    InitVars
    0.80
    Activations Density 0.733%

    No Known Activations