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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9102
    Prev
    Next
    INDEX
    Explanations

    phrases with time, and scores well on the phrases "all-time" and "a long time"

    oai_token-act-pair · gemini-2.0-flash

    technical language and time references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Time
    -3.03
    Time
    -2.92
     time
    -2.92
     TIME
    -2.75
    time
    -2.64
    TIME
    -2.56
    时间
    -2.03
     getTime
    -2.00
     Zeit
    -2.00
     tijd
    -1.93
    POSITIVE LOGITS
    DockStyle
    0.65
    ंदीखरीदारी
    0.56
    parsedMessage
    0.54
    Autoritní
    0.52
    RegistryLite
    0.50
     ویکی‌پدی
    0.46
    Atsauces
    0.46
    PreferredItem
    0.45
    reactstrap
    0.44
    quín
    0.43
    Activations Density 2.681%

    No Known Activations