© 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. 12086
    Prev
    Next
    INDEX
    Explanations

    Java code, identifying package names, import statements, and other code-related keywords.

    oai_token-act-pair · gemini-2.0-flash

    com

    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
     enmity
    -0.39
     hotter
    -0.38
    Allocated
    -0.38
    NoStop
    -0.36
    IntoConstraints
    -0.36
     fermented
    -0.36
    ighed
    -0.36
     offensively
    -0.36
     vuitton
    -0.35
     spati
    -0.35
    POSITIVE LOGITS
    bukkit
    0.78
    WebServlet
    0.76
    invokeLater
    0.76
    DockStyle
    0.75
     AssemblyCulture
    0.74
     CreateTagHelper
    0.72
    picasso
    0.72
    SuppressMessage
    0.69
     UIApplication
    0.67
    mybatisplus
    0.66
    Activations Density 9.811%

    No Known Activations