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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4357
    Prev
    Next
    INDEX
    Explanations

    the words "wait", "waiting", or "waited", sometimes also picking up on related words like "takes" or "vice".

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "wait"

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

    wait

    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
    CppCodeGen
    -0.89
     يتيمه
    -0.86
    enderror
    -0.84
    EDEFAULT
    -0.78
     Vikipedi
    -0.77
    ItemBackground
    -0.75
     tartalomajánló
    -0.73
     HasFactory
    -0.73
    RenderAtEndOf
    -0.72
    MessageTagHelper
    -0.72
    POSITIVE LOGITS
     for
    0.95
     till
    0.76
     until
    0.74
     til
    0.63
     on
    0.53
    till
    0.51
     to
    0.50
    until
    0.48
    for
    0.47
    Until
    0.45
    Activations Density 1.683%

    No Known Activations