© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4600
    Prev
    Next
    INDEX
    Explanations

    references to quantifying video or experimental results

    oai_token-act-pair · gemini-2.0-flash

    the word "per"

    np_token-act-pair-logits · gpt-4o-mini

    per

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     disambiguazione
    -0.83
    mybatisplus
    -0.78
    expandindo
    -0.72
    .*")]
    -0.71
    makeConstraints
    -0.62
    MigrationBuilder
    -0.59
    oplayer
    -0.57
    Datuak
    -0.57
     Normdatei
    -0.56
    transQ
    -0.56
    POSITIVE LOGITS
     per
    1.94
    per
    1.45
    Per
    1.32
     Per
    1.27
     PER
    1.23
    PER
    1.09
    ต่อ
    0.96
     प्रति
    0.92
     $/
    0.90
    /
    0.88
    Activations Density 2.593%

    No Known Activations