© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    equations/mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    LaTeX code

    np_max-act · gemini-2.0-flash

    say "LaTeX commands" Method used: 2 — because following tokens are math/LaTeX macros, so the neuron detects LaTeX commands

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Примечания
    -0.65
    Bronnen
    -0.57
    ГЛА
    -0.56
    +#+#
    -0.53
    /~
    -0.51
    Rhestr
    -0.51
    Ссылки
    -0.50
    posedge
    -0.49
    　　……
    -0.49
    SaveChangesAsync
    -0.48
    POSITIVE LOGITS
    <bos>
    0.66
    astify
    0.65
     écl
    0.63
    DrawerToggle
    0.60
     =[]
    0.57
    ,’’
    0.55
    });*/
    0.54
     grito
    0.53
    ",(
    0.52
    Scanner
    0.52
    Activations Density 4.882%

    No Known Activations