© 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. 220
    Prev
    Next
    INDEX
    Explanations

    code-related words and namespace usages

    oai_token-act-pair · gemini-2.0-flash

    code and file paths

    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
     Normdatei
    -0.60
     podjela
    -0.55
    sizeCache
    -0.53
     היתה
    -0.53
     management
    -0.52
    ();)
    -0.51
     ddelweddau
    -0.51
    Wady
    -0.50
     design
    -0.48
    )++;
    -0.48
    POSITIVE LOGITS
    TestingModule
    0.78
    BASEPATH
    0.66
    Cryptography
    0.64
    ConverterFactory
    0.63
    ArgumentParser
    0.62
    AndroidJUnit
    0.62
     GenerationType
    0.62
    WebServlet
    0.61
    SpringRunner
    0.60
    makeConstraints
    0.58
    Activations Density 16.162%

    No Known Activations