© 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. 5939
    Prev
    Next
    INDEX
    Explanations

    the word "take" followed by another word

    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
    Take
    -0.91
     take
    -0.90
    take
    -0.89
     taking
    -0.87
    taking
    -0.86
     taken
    -0.85
    Taking
    -0.84
    Taken
    -0.82
    taken
    -0.81
     Take
    -0.81
    POSITIVE LOGITS
    PhysRevLett
    0.51
     suivants
    0.49
    Viitteet
    0.49
     Travers
    0.47
     ويكيميديا
    0.45
     heapq
    0.45
    日閲覧
    0.45
     whistle
    0.45
     Watson
    0.44
     Sora
    0.44
    Activations Density 3.634%

    No Known Activations