© 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. 11987
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business and finance

    oai_token-act-pair · gemini-2.0-flash

    terms related to auditing and company regulations

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

    Companies

    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
     anſ
    -0.73
     Anſ
    -0.68
    ніципа
    -0.68
     Jefus
    -0.64
    findpost
    -0.64
     chofe
    -0.61
     OMITBAD
    -0.58
     poffe
    -0.58
     neceff
    -0.58
     Савезне
    -0.57
    POSITIVE LOGITS
     companies
    0.56
    Билгалдахарш
    0.53
    imwrite
    0.52
    Personensuche
    0.47
    HttpFoundation
    0.46
    companies
    0.44
    ForTesting
    0.44
     players
    0.44
     inputStream
    0.44
     company
    0.43
    Activations Density 1.908%

    No Known Activations