© 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. 9410
    Prev
    Next
    INDEX
    Explanations

    words in online reviews about finding good companies

    oai_token-act-pair · 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
     оригіналу
    -0.73
     Inscrivez
    -0.63
    migrationBuilder
    -0.61
    Бахар
    -0.60
    IsContent
    -0.60
    Autoritní
    -0.59
    Xaml
    -0.57
     للمعارف
    -0.57
    $_['
    -0.56
     NUKAT
    -0.56
    POSITIVE LOGITS
     stock
    0.51
     Stock
    0.49
    HKEY
    0.48
     CWE
    0.48
    Stock
    0.48
    urlencoded
    0.47
     consign
    0.47
    inguished
    0.47
    檔
    0.45
    ładka
    0.44
    Activations Density 3.149%

    No Known Activations