© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 1199
    Prev
    Next
    INDEX
    Explanations

    python code initialization and special methods like `__init__`, `__iter__`, `__len__`, and `__getattr__`

    oai_token-act-pair · gemini-2.0-flash

    Underscores

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ."),
    -1.06
     itſelf
    -1.03
    .")
    
    -1.03
     myſelf
    -1.02
     Efq
    -0.99
    tvguidetime
    -0.98
     />);
    -0.98
    )»
    -0.97
    .");
    
    -0.97
    "):
    
    -0.96
    POSITIVE LOGITS
    __
    1.05
    ___
    0.98
     __
    0.98
    ____
    0.95
    ***
    0.92
    *****
    0.90
    ______
    0.89
    ________________
    0.87
     ___
    0.87
     ____
    0.87
    Activations Density 4.703%

    No Known Activations