© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12681
    Prev
    Next
    INDEX
    Explanations

    code snippets, file names, and directory structures

    oai_token-act-pair · gemini-2.0-flash

    file-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    file extensions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagHelperRunner
    -0.93
    WaitGroup
    -0.82
    ThroughAttribute
    -0.82
     שוליים
    -0.81
    setVerticalGroup
    -0.79
    Gambas
    -0.78
     &___
    -0.77
    ]--;
    -0.77
     通販
    -0.76
     GenerationType
    -0.75
    POSITIVE LOGITS
     file
    0.47
     internal
    0.45
     added
    0.41
    ati
    0.40
    Intern
    0.40
     common
    0.40
     Intern
    0.39
     f
    0.39
     in
    0.39
     line
    0.39
    Activations Density 1.075%

    No Known Activations