© 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. 7885
    Prev
    Next
    INDEX
    Explanations

    words related to internet speed and wireless connection

    oai_token-act-pair · gemini-2.0-flash

    WiFi and internet

    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
    Hentet
    -0.67
    addCriterion
    -0.64
    Дереккөздер
    -0.62
    出版年
    -0.62
    ValueStyle
    -0.59
    fjspx
    -0.59
    UnitTesting
    -0.59
    XmlAccessType
    -0.56
    Connect
    -0.56
     ivelany
    -0.56
    POSITIVE LOGITS
     endregion
    0.53
     @}
    0.50
     MonoBehaviour
    0.49
     Neutr
    0.49
     "]";
    0.48
    meris
    0.48
     '+':
    0.47
    unicaciones
    0.47
     "}";
    0.47
    saraba
    0.46
    Activations Density 3.489%

    No Known Activations