© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6521
    Prev
    Next
    INDEX
    Explanations

    time intervals or when a task should be regularly performed or checked

    oai_token-act-pair · gemini-2.0-flash

    Regular intervals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    -0.72
    脚注の使い方
    -0.63
     privées
    -0.51
     Перейти
    -0.50
     للمعارف
    -0.49
     razu
    -0.48
     AssemblyCulture
    -0.47
    日目
    -0.46
     considérons
    -0.45
     arşivlendi
    -0.45
    POSITIVE LOGITS
     periodically
    1.12
     regularity
    1.08
     regularly
    1.06
     periodic
    1.04
    regular
    1.01
     setInterval
    0.99
    setInterval
    0.98
     regular
    0.98
    Periodic
    0.94
     interval
    0.93
    Activations Density 0.860%

    No Known Activations