© 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. 9175
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode formatting, specifically the "\mathrm" command

    oai_token-act-pair · gemini-2.0-flash

    mathrm

    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
     transférez
    -0.67
    最快更新
    -0.65
    parsedMessage
    -0.65
    Jîn
    -0.62
    Poloha
    -0.62
    bootstrapcdn
    -0.60
    DataSnapshot
    -0.58
    Newswire
    -0.58
    principalColumn
    -0.57
     OkHttpClient
    -0.57
    POSITIVE LOGITS
    ScopeManager
    0.40
    /__
    0.36
    onViewCreated
    0.35
    ->_
    0.33
    toHaveBeenCalled
    0.32
     bocca
    0.32
    CharStream
    0.32
     SPDX
    0.32
    oneph
    0.31
    (*)
    0.31
    Activations Density 2.592%

    No Known Activations