© 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. 13212
    Prev
    Next
    INDEX
    Explanations

    dates, days of the week, and certain words related to copyright, software development, and user interaction

    oai_token-act-pair · gemini-2.0-flash

    imperative verbs or suggestions

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

    technical instructions

    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
    PyExc
    -0.58
    RegistryLite
    -0.53
    وفاته
    -0.52
    numerusform
    -0.52
    czywiście
    -0.50
    StoryboardSegue
    -0.50
    
    -0.50
     ujednoznacz
    -0.46
    ")));
    -0.46
    libft
    -0.45
    POSITIVE LOGITS
     try
    1.27
     consider
    1.14
     ask
    1.06
     check
    1.05
     remember
    1.02
     ensure
    1.01
     choose
    0.98
     keep
    0.96
     observe
    0.94
     take
    0.94
    Activations Density 3.981%

    No Known Activations