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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9073
    Prev
    Next
    INDEX
    Explanations

    words related to studies, research, and publication

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    L
    -1.61
    R
    -1.49
    G
    -1.32
    S
    -1.29
    T
    -1.28
    M
    -1.28
    r
    -1.22
    l
    -1.21
    D
    -1.21
     L
    -1.19
    POSITIVE LOGITS
     Wiktionnaire
    0.69
     disambiguazione
    0.63
    SharedDtor
    0.57
     الحره
    0.55
     חיצוניים
    0.54
     سكانية
    0.53
     surla
    0.53
    таратура
    0.52
     initComponents
    0.52
    GEBURTSDATUM
    0.51
    Activations Density 45.157%

    No Known Activations