© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11412
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and characters within a stylized data format

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ⓧ
    -0.85
    存于互联网档案馆
    -0.79
     Paglinawan
    -0.72
    niająca
    -0.67
     Theſe
    -0.66
     jScrollPane
    -0.66
    ConstraintMaker
    -0.65
     <=",
    -0.63
    omotor
    -0.63
     intptr
    -0.63
    POSITIVE LOGITS
    <eos>
    0.49
    try
    0.45
    ClientRect
    0.44
     
    0.44
    hoc
    0.43
    </blockquote>
    0.42
     […]
    0.42
     touch
    0.40
     try
    0.40
    Accent
    0.40
    Activations Density 1.563%

    No Known Activations