© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8507
    Prev
    Next
    INDEX
    Explanations

    sentences discussing decisions and choices, specifically in the context of "you" or "we"

    oai_token-act-pair · gemini-2.0-flash

    say "make"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Made
    -2.88
     Made
    -2.81
    made
    -2.78
     made
    -2.70
     MADE
    -2.63
    MADE
    -2.50
    Making
    -1.77
    make
    -1.74
     Making
    -1.74
    Make
    -1.70
    POSITIVE LOGITS
    ItemBackground
    0.30
     пове
    0.28
    rzej
    0.28
    孀
    0.27
    ByName
    0.27
    URI
    0.27
    ավ
    0.27
    פת
    0.26
    تاريخ
    0.26
    omiya
    0.26
    Activations Density 1.831%

    No Known Activations