© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5699
    Prev
    Next
    INDEX
    Explanations

    the word "you" along with words related to programming and software usage

    oai_token-act-pair · gemini-2.0-flash

    programming references or constructs

    np_token-act-pair-logits · gpt-4o-mini

    you/we

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    BeginContext
    -0.48
    idavit
    -0.48
     prayed
    -0.48
    Worked
    -0.47
     javafx
    -0.47
     mergeFrom
    -0.47
     intracellular
    -0.46
    itness
    -0.46
     Worked
    -0.45
     _{
    -0.44
    POSITIVE LOGITS
    protoimpl
    0.72
     Baillargeon
    0.65
     okuyayım
    0.64
    TagMode
    0.64
    Organisateur
    0.62
    AddTagHelper
    0.61
     himo
    0.59
    ğından
    0.59
    :✨
    0.55
    GIH
    0.54
    Activations Density 3.496%

    No Known Activations