© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6228
    Prev
    Next
    INDEX
    Explanations

    words related to time and dates, often in a historical context

    oai_token-act-pair · gemini-2.0-flash

    when

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    قایناقلار
    -0.93
    ThroughAttribute
    -0.90
    OGND
    -0.77
     propOrder
    -0.76
     defaultstate
    -0.75
    ########.
    -0.71
    homonymie
    -0.69
     Audiodateien
    -0.68
    قایناق‌لار
    -0.68
     transférez
    -0.66
    POSITIVE LOGITS
     when
    3.03
    when
    2.45
     cuando
    2.25
     quando
    2.20
     WHEN
    2.05
     When
    1.98
    When
    1.92
     lorsque
    1.88
     когда
    1.84
    cuando
    1.82
    Activations Density 8.105%

    No Known Activations