© 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. 13277
    Prev
    Next
    INDEX
    Explanations

    words related to questions and requests

    oai_token-act-pair · gemini-2.0-flash

    Romance languages

    np_max-act-logits · gemini-2.0-flash

    prepositions/articles

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     stället
    -1.02
     vérit
    -0.96
     mères
    -0.95
     prêtres
    -0.95
     genoux
    -0.94
     enfans
    -0.94
     supérieurs
    -0.94
     réfrig
    -0.94
     âmes
    -0.93
     fermés
    -0.93
    POSITIVE LOGITS
     Cæsar
    0.25
     Sopho
    0.20
     Oggi
    0.19
     Tutto
    0.18
     Ogni
    0.17
     Athenians
    0.17
     Certo
    0.17
     Că
    0.17
     Shakspeare
    0.16
     Altri
    0.16
    Activations Density 48.680%

    No Known Activations