© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12056
    Prev
    Next
    INDEX
    Explanations

    mentions of doing things from time to time.

    oai_token-act-pair · gemini-2.0-flash

    the concept of time

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

    say "time"

    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
    Espèce
    -0.43
    esez
    -0.42
    reciate
    -0.37
     minOccurs
    -0.37
    Mediabestanden
    -0.37
    hnout
    -0.37
    RTEE
    -0.36
    simmon
    -0.35
     zewnętrzne
    -0.35
    AGON
    -0.35
    POSITIVE LOGITS
     time
    3.42
    time
    2.56
     TIME
    2.25
    Time
    2.23
     Time
    2.20
    TIME
    1.96
     tijd
    1.93
     времени
    1.85
    时间
    1.85
     tiempo
    1.83
    Activations Density 2.201%

    No Known Activations