© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4199
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms such as function names and list operations

    oai_token-act-pair · gemini-2.0-flash

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ApiException
    -0.44
     hasNext
    -0.42
    HomeAsUpEnabled
    -0.41
    blockList
    -0.39
    useEffect
    -0.38
    mention
    -0.38
     œufs
    -0.38
     separ
    -0.38
    stringBuffer
    -0.38
    setSubject
    -0.37
    POSITIVE LOGITS
    <bos>
    0.79
    ValueStyle
    0.71
    OGND
    0.67
     Waray
    0.59
    afficheront
    0.59
    يكب
    0.57
     Italijani
    0.56
     تضيفلها
    0.56
    UnusedPrivate
    0.55
    ItemBackground
    0.55
    Activations Density 16.659%

    No Known Activations