© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9050
    Prev
    Next
    INDEX
    Explanations

    times and date formats, and possibly also abbreviations or codes.

    oai_token-act-pair · gemini-2.0-flash

    dates, times, codes

    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
     Seventh
    -0.90
     seventh
    -0.85
    Seventh
    -0.81
     Seventy
    -0.75
     Eighth
    -0.74
    ="@+
    -0.73
     Seven
    -0.73
     eighth
    -0.71
    новниш
    -0.70
    MockBean
    -0.70
    POSITIVE LOGITS
    4
    0.76
    5
    0.63
    3
    0.59
     fourth
    0.54
    ４
    0.53
     five
    0.48
    2
    0.48
     Five
    0.47
     four
    0.47
    five
    0.47
    Activations Density 3.024%

    No Known Activations