© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 14370
    Prev
    Next
    INDEX
    Explanations

    scientific or legal writing, as shown by references like "Ref" and "Docket", equations, citations, and other domain-specific terminology.

    oai_token-act-pair · gemini-2.0-flash

    Ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    thage
    -0.60
     مرئيه
    -0.53
     الرياضيه
    -0.52
    __':
    -0.51
     становника
    -0.51
     FetchType
    -0.50
     tromper
    -0.50
    Ծանոթ
    -0.49
    ledem
    -0.49
     gawas
    -0.48
    POSITIVE LOGITS
     disambiguazione
    0.68
     -->>
    0.58
    InjectAttribute
    0.57
    EDEFAULT
    0.56
     natale
    0.56
    fjspx
    0.54
     annuel
    0.53
     '\''
    0.53
     Majefty
    0.53
     Sabina
    0.52
    Activations Density 21.414%

    No Known Activations