© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6346
    Prev
    Next
    INDEX
    Explanations

    code, especially python code with imports, try/except blocks, and other control flow statements

    oai_token-act-pair · gemini-2.0-flash

    programming keywords and constructs

    np_token-act-pair-logits · gpt-4o-mini

    import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    X
    -0.45
    ×
    -0.45
    Single
    -0.45
    over
    -0.44
     investigadores
    -0.43
    x
    -0.42
    ixel
    -0.42
     isolato
    -0.42
    single
    -0.42
    dr
    -0.41
    POSITIVE LOGITS
    CppMethod
    0.93
    ImageContext
    0.88
    MemoryWarning
    0.82
    出版年
    0.79
    sidemargin
    0.76
    TagMode
    0.75
    rungsseite
    0.75
    ValueStyle
    0.74
    TypedDataSet
    0.73
     Réponses
    0.73
    Activations Density 0.437%

    No Known Activations