© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12063
    Prev
    Next
    INDEX
    Explanations

    words related to industrial production

    oai_token-act-pair · gemini-2.0-flash

    terms related to production and manufacturing

    np_token-act-pair-logits · gpt-4o-mini

    production

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    #+#
    -0.89
    DrawerToggle
    -0.56
    ándor
    -0.55
     beginnetje
    -0.55
     Endowment
    -0.54
    ंदीखरीदारी
    -0.52
    ineno
    -0.52
    SpringBootTest
    -0.52
     Dossier
    -0.51
     Midway
    -0.50
    POSITIVE LOGITS
     Signalez
    0.53
    ">//
    0.52
     Unies
    0.52
     gefeiert
    0.47
     organisée
    0.46
    holdet
    0.46
    tagHelperRunner
    0.46
    indd
    0.45
     såsom
    0.45
    יתוף
    0.44
    Activations Density 7.363%

    No Known Activations