© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3364
    Prev
    Next
    INDEX
    Explanations

    the word 'time' (optionally preceded by another non-zero-activation word of interest)

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "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
    reactstrap
    -0.52
    AndEndTag
    -0.47
    Geografía
    -0.41
    ugc
    -0.41
    nande
    -0.40
    quium
    -0.39
    ющийся
    -0.38
    nonatomic
    -0.37
    իր
    -0.37
     Pokies
    -0.37
    POSITIVE LOGITS
     time
    3.20
     times
    3.11
    time
    2.34
    times
    2.33
     TIME
    2.23
     Time
    2.19
     TIMES
    2.19
    Time
    2.14
     Times
    2.13
    Times
    2.13
    Activations Density 2.866%

    No Known Activations