© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5431
    Prev
    Next
    INDEX
    Explanations

    forms of the verb to have

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming syntax

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

    have has

    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
     estekak
    -0.60
     allons
    -0.50
    -------------</
    -0.49
    thâu
    -0.48
     wollt
    -0.45
    kuuta
    -0.45
    IInterface
    -0.45
     pernah
    -0.45
     ändå
    -0.44
    yorlar
    -0.44
    POSITIVE LOGITS
    EndInit
    0.73
    StoreMessageInfo
    0.70
    webElementXpaths
    0.69
    /**
    0.64
     just
    0.60
     arriving
    0.60
    rodow
    0.57
    :✨
    0.57
    сылкі
    0.57
    MessageTagHelper
    0.56
    Activations Density 1.011%

    No Known Activations