© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10535
    Prev
    Next
    INDEX
    Explanations

    mentions of "time" or time-related things, particularly the lack of time in the context of work or jobs

    oai_token-act-pair · gemini-2.0-flash

    managing time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     lenker
    -0.53
     Савезне
    -0.50
     couple
    -0.48
     benach
    -0.47
     next
    -0.46
    twig
    -0.46
    nasel
    -0.46
    Kilder
    -0.45
     Mathis
    -0.45
    ėms
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.79
    ConstraintMaker
    0.69
     ExecuteAsync
    0.68
    OrWhiteSpace
    0.65
    onavir
    0.64
    κτηρισ
    0.61
    SBATCH
    0.59
     Signalez
    0.58
    ruptedException
    0.58
    министра
    0.56
    Activations Density 0.927%

    No Known Activations