© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14997
    Prev
    Next
    INDEX
    Explanations

    references, citations, or examples being discussed or used in an argument

    oai_token-act-pair · gemini-2.0-flash

    Citing

    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
     initComponents
    -0.68
     Paglinawan
    -0.68
     xlink
    -0.64
     Sphinx
    -0.53
    nodoc
    -0.53
     uintptr
    -0.53
     Ganzen
    -0.53
     autorytatywna
    -0.51
    Concurrency
    -0.51
     vulgaris
    -0.50
    POSITIVE LOGITS
    InjectAttribute
    0.68
    AutoScale
    0.51
    ImageContext
    0.50
    telser
    0.48
    \{\\
    0.47
    )’
    0.47
    <_>
    0.47
     seraient
    0.46
    SuppressWarnings
    0.45
    setCellValue
    0.44
    Activations Density 0.761%

    No Known Activations