© 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. 4792
    Prev
    Next
    INDEX
    Explanations

    words related to computing, internet, electronics, programming, and engineering

    oai_token-act-pair · gemini-2.0-flash

    technical information

    np_max-act-logits · gemini-2.0-flash

    plural s

    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
    chenkt
    -0.55
    pannt
    -0.55
    prechpartner
    -0.48
    chränk
    -0.47
    indépendance
    -0.43
    chieht
    -0.42
    ennemi
    -0.39
    chossen
    -0.39
     neutre
    -0.39
     leçons
    -0.38
    POSITIVE LOGITS
    haped
    1.00
    tep
    0.97
    heet
    0.96
    mith
    0.95
    heets
    0.95
    hape
    0.93
    ub
    0.90
    ystem
    0.90
    creen
    0.89
    teps
    0.89
    Activations Density 37.165%

    No Known Activations