© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5501
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup, a language for typesetting documents

    oai_token-act-pair · gemini-2.0-flash

    LaTeX code

    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
    ，
    -1.05
     ，
    -0.83
     ،
    -0.81
    ，“
    -0.75
    ；
    -0.72
    ，《
    -0.70
    ،
    -0.67
    ，「
    -0.66
    .,
    -0.65
    POSITIVE LOGITS
     Paglinawan
    0.56
    ̍t
    0.55
     Chwiliwch
    0.54
    soort
    0.54
    الإنجليزية
    0.53
    kmale
    0.52
     Ajoutez
    0.52
     banques
    0.51
     rhestr
    0.50
     pictograms
    0.50
    Activations Density 2.634%

    No Known Activations