© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15838
    Prev
    Next
    INDEX
    Explanations

    mentions of mathematical symbols and equations

    oai_token-act-pair · gemini-2.0-flash

    R

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Selb
    -0.43
     canina
    -0.40
     Title
    -0.40
     colorWith
    -0.39
    лыша
    -0.38
     met
    -0.38
    AndPassword
    -0.37
    透
    -0.37
    ClientRect
    -0.37
    рик
    -0.36
    POSITIVE LOGITS
    BufferException
    1.09
    ########.
    1.04
    contentLoaded
    0.91
     resourceCulture
    0.86
     متعلقه
    0.85
    Datuak
    0.79
     Италијани
    0.77
     تضيفلها
    0.76
     pinulongan
    0.76
    bewerken
    0.75
    Activations Density 6.551%

    No Known Activations