© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6234
    Prev
    Next
    INDEX
    Explanations

    words related to computer hardware components and timing

    oai_token-act-pair · gemini-2.0-flash

    clock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     clock
    -2.78
    clock
    -2.45
     Clock
    -2.39
    Clock
    -2.33
     clocks
    -2.14
     CLOCK
    -2.13
     Clocks
    -1.91
    CLOCK
    -1.87
     clocked
    -1.67
     horloge
    -1.54
    POSITIVE LOGITS
    DOCTYPE
    0.65
     yii
    0.48
    Hauptartikel
    0.47
     defStyleAttr
    0.47
     <=",
    0.44
    Hik
    0.43
     Commencez
    0.43
    ätt
    0.43
    aknya
    0.42
    -------------</
    0.41
    Activations Density 1.625%

    No Known Activations