© 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. 5708
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to economy, money and mathematics

    oai_token-act-pair · gemini-2.0-flash

    action verbs

    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
     being
    -2.02
    Being
    -1.97
     Being
    -1.92
    being
    -1.88
     BEING
    -1.76
     étant
    -1.45
     essere
    -1.03
     sendo
    -1.00
     fiind
    -0.98
     siendo
    -0.96
    POSITIVE LOGITS
     placing
    0.84
     putting
    0.83
     introducing
    0.80
     assigning
    0.75
     awarding
    0.74
     specifying
    0.73
     applying
    0.72
     defining
    0.71
     adding
    0.71
     enforcing
    0.70
    Activations Density 15.490%

    No Known Activations