© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7024
    Prev
    Next
    INDEX
    Explanations

    words related to technology and the internet

    oai_token-act-pair · gemini-2.0-flash

    terms related to speed

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

    Internet speed

    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
    脚注の使い方
    -0.74
     تضيفلها
    -0.69
    ISupport
    -0.65
    PerformLayout
    -0.62
    makeConstraints
    -0.61
     <>",
    -0.61
     MonoBehaviour
    -0.59
    MENAFN
    -0.57
    rrggbb
    -0.56
     /\.(
    -0.56
    POSITIVE LOGITS
     speed
    0.67
    peed
    0.65
     speeds
    0.61
    speed
    0.56
     SPEED
    0.53
     rych
    0.52
     kecepatan
    0.52
    Speed
    0.51
     chóng
    0.50
     Speeds
    0.50
    Activations Density 1.614%

    No Known Activations