© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11
    Prev
    Next
    INDEX
    Explanations

    Swedish names and words, especially those related to a specific family

    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
    thday
    -0.62
    HtmlAttribute
    -0.60
     onOptions
    -0.59
    رشف
    -0.57
    IsContent
    -0.55
     initComponents
    -0.55
     للاسماء
    -0.54
     benessere
    -0.54
     विश्वसनीयता
    -0.54
    katapos
    -0.54
    POSITIVE LOGITS
    Bata
    0.60
     erk
    0.53
     känna
    0.50
    Източници
    0.50
    }?
    0.49
    rxjs
    0.48
     Wiktionnaire
    0.47
    flink
    0.46
     veta
    0.46
    RegressionTest
    0.45
    Activations Density 0.622%

    No Known Activations