© 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. 14231
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time

    oai_token-act-pair · gemini-2.0-flash

    references to time or past events

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

    the past

    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
    WireFormatLite
    -0.75
    ValueStyle
    -0.53
    InputTagHelper
    -0.51
     ISNI
    -0.49
     cherchés
    -0.49
    glio
    -0.45
    celes
    -0.44
     oprot
    -0.41
    tzmann
    -0.41
    forName
    -0.41
    POSITIVE LOGITS
     previous
    2.81
    previous
    2.52
     Previous
    2.41
    Previous
    2.38
     past
    2.33
     recent
    2.20
     PREVIOUS
    2.17
     earlier
    2.11
     previously
    2.11
    Previously
    2.02
    Activations Density 7.919%

    No Known Activations