© 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. 3931
    Prev
    Next
    INDEX
    Explanations

    the verb "take" and its variations

    oai_token-act-pair · gemini-2.0-flash

    take

    np_max-act-logits · 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
     Meksiku
    -0.86
    ReusableCell
    -0.77
    XmlAccessorType
    -0.74
    niająca
    -0.74
    GraphicsUnit
    -0.73
    AndEndTag
    -0.73
     AssemblyProduct
    -0.72
    脚注の使い方
    -0.71
    )++;
    -0.71
    bootstrapcdn
    -0.69
    POSITIVE LOGITS
    take
    0.54
     take
    0.53
     Take
    0.50
    on
    0.48
    Take
    0.48
    pal
    0.44
    try
    0.44
     definition
    0.43
     TAKE
    0.41
     tider
    0.41
    Activations Density 2.252%

    No Known Activations