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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7707
    Prev
    Next
    INDEX
    Explanations

    code-related keywords like serialize, json, string, instantiation, async, containers, debugging, shared folders, and UI events

    oai_token-act-pair · gemini-2.0-flash

    serialize

    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
     QWidget
    -0.89
     CGPoint
    -0.74
     JLabel
    -0.71
     tslint
    -0.69
    redirects
    -0.68
    JLabel
    -0.68
     signUp
    -0.67
     usize
    -0.66
     clearColor
    -0.66
     println
    -0.65
    POSITIVE LOGITS
     Monfieur
    1.05
    RenderAtEndOf
    0.95
    RegressionTest
    0.91
     ProtoMessage
    0.90
     purpoſe
    0.84
    setVerticalGroup
    0.84
     оригіналу
    0.79
     uſe
    0.78
    parsedMessage
    0.76
     Eſ
    0.76
    Activations Density 4.716%

    No Known Activations