© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 459
    Prev
    Next
    INDEX
    Explanations

    a variety of HTML markup, numerical character codes, and other code-related syntax.

    oai_token-act-pair · gemini-2.0-flash

    Code and legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    InjectAttribute
    -0.74
    mergeFrom
    -0.73
    RenderAtEndOf
    -0.72
     NSCoder
    -0.71
    rungsseite
    -0.62
     nakalista
    -0.62
     <>",
    -0.60
    IsContent
    -0.60
    KURZBESCHREIBUNG
    -0.60
     متعلقه
    -0.60
    POSITIVE LOGITS
    1
    1.63
    １
    1.04
     ১
    0.88
    ১
    0.83
     १
    0.81
     ١
    0.67
     twelve
    0.67
    ۱
    0.66
    १
    0.66
     Twelve
    0.65
    Activations Density 10.158%

    No Known Activations