© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10394
    Prev
    Next
    INDEX
    Explanations

    code related to networking and data fields, often within a module

    oai_token-act-pair · gemini-2.0-flash

    Computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    NUMX
    -1.16
    ftagPool
    -1.13
    ^(@)
    -1.13
     EconPapers
    -1.11
    IsMutable
    -1.05
     <>",
    -1.05
    ImageContext
    -1.03
    oredCriteria
    -1.02
     propOrder
    -1.02
    IntoConstraints
    -1.02
    POSITIVE LOGITS
    <bos>
    1.62
    ↵↵
    1.15
    ↵
    0.99
    '
    0.95
    (
    0.81
    1
    0.76
    2
    0.75
    \
    0.71
    The
    0.70
    .
    0.70
    Activations Density 2.337%

    No Known Activations