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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10854
    Prev
    Next
    INDEX
    Explanations

    lines of code that import packages

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    DockStyle
    -0.88
    tvguidetime
    -0.86
    featureID
    -0.84
     للاسماء
    -0.80
     ویکی‌پدی
    -0.80
     doInBackground
    -0.78
    
    -0.77
     onOptions
    -0.77
    новниш
    -0.75
    تقاوى
    -0.75
    POSITIVE LOGITS
     '
    0.60
    '
    0.52
    ('
    0.43
    '.
    0.40
    стави
    0.37
    義
    0.36
    сан
    0.36
    @
    0.36
    "
    0.35
    ',
    0.35
    Activations Density 0.834%

    No Known Activations