© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12631
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate a time sequence

    oai_token-act-pair · gemini-2.0-flash

    Time/sequential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    archiviato
    -0.60
    WriteBarrier
    -0.57
     tartalomajánló
    -0.56
    FOOTNOTES
    -0.56
    MarshalTo
    -0.55
    MeasureSpec
    -0.54
    initWithFrame
    -0.54
    AndroidJUnit
    -0.52
    offsetof
    -0.50
    InSection
    -0.50
    POSITIVE LOGITS
     later
    1.55
    later
    1.39
    Later
    1.30
     Later
    1.25
     LATER
    1.22
     später
    1.20
     späteren
    1.13
     później
    1.08
     позже
    1.04
     senare
    1.03
    Activations Density 1.530%

    No Known Activations