© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11007
    Prev
    Next
    INDEX
    Explanations

    code, lists, and parenthetical statements from different languages, marking endings and pauses

    oai_token-act-pair · gemini-2.0-flash

    after separator

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    complexType
    -0.59
    richTextPanel
    -0.56
     AssemblyTitle
    -0.53
    CppMethod
    -0.48
    <bos>
    -0.47
    tabular
    -0.46
     propOrder
    -0.46
    ItemBackground
    -0.45
    ше
    -0.43
    uns
    -0.43
    POSITIVE LOGITS
    "}")
    0.62
    }}/>
    0.62
     becauſe
    0.61
     nôtre
    0.60
    NUMX
    0.60
    latego
    0.60
    mặt
    0.59
    __.__
    0.59
     تضيفلها
    0.59
     devint
    0.59
    Activations Density 0.784%

    No Known Activations