© 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. 1613
    Prev
    Next
    INDEX
    Explanations

    phrases used when providing formal and/or technical explanations or descriptions of something

    oai_token-act-pair · gemini-2.0-flash

    those

    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
     aceste
    -0.66
     typelib
    -0.54
    ChildScrollView
    -0.54
     betweenstory
    -0.52
     pulumi
    -0.52
    SequentialGroup
    -0.51
    fromnode
    -0.50
    TintMode
    -0.48
    RegressionTest
    -0.48
    abetes
    -0.47
    POSITIVE LOGITS
     those
    3.58
    Those
    3.27
    those
    3.25
     Those
    3.14
     THOSE
    2.66
    那些
    2.08
     ceux
    2.06
     aqueles
    1.96
     thoſe
    1.94
     aquellos
    1.88
    Activations Density 5.072%

    No Known Activations