© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10334
    Prev
    Next
    INDEX
    Explanations

    instances of the word "light" with its surrounding context

    oai_token-act-pair · gemini-2.0-flash

    narrative, belonging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    abestanden
    -0.76
    脚注の使い方
    -0.76
    ArrowToggle
    -0.70
    )++;
    -0.68
     ddelweddau
    -0.68
    DockStyle
    -0.68
    RenderAtEndOf
    -0.66
     المعيارى
    -0.64
     betweenstory
    -0.64
    tagHelperRunner
    -0.64
    POSITIVE LOGITS
     san
    0.50
    onHide
    0.47
     regular
    0.47
    arXiv
    0.45
    HasIndex
    0.44
    man
    0.43
     their
    0.42
    u
    0.41
    WebVitals
    0.41
    afd
    0.40
    Activations Density 0.306%

    No Known Activations