© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    tokens occuring often in legal opinions and technical specifications, including numbers, characters representing section markers, and parenthetical phrases.

    oai_token-act-pair · gemini-2.0-flash

    formal documents

    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
     nephe
    -0.37
    <bos>
    -0.36
     toledo
    -0.35
     Parli
    -0.32
     Polyn
    -0.30
     camels
    -0.30
     obsidian
    -0.29
     chanter
    -0.28
     conch
    -0.27
     Phoen
    -0.26
    POSITIVE LOGITS
     pinulongan
    1.13
    Personendaten
    1.12
    WriteBarrier
    1.11
     समीक्षाओं
    1.03
    webElementXpaths
    1.02
     surla
    1.02
    verwijspagina
    1.00
     تضيفلها
    1.00
    Datuak
    0.98
    rungsseite
    0.98
    Activations Density 55.349%

    No Known Activations