© 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. 5719
    Prev
    Next
    INDEX
    Explanations

    instances of "at a time."

    oai_token-act-pair · gemini-2.0-flash

    phrases starting with 'at'

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

    "at a time"

    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
     esternos
    -0.76
    addCriterion
    -0.76
    ⓧ
    -0.75
     propOrder
    -0.73
     Roskov
    -0.70
    InitVars
    -0.70
    principalTable
    -0.69
    awtextra
    -0.68
    ValueGenerated
    -0.68
    Демографія
    -0.65
    POSITIVE LOGITS
    ITHUB
    0.45
     poi
    0.43
     Main
    0.43
    onel
    0.43
     alatt
    0.43
    stehen
    0.42
     StatefulWidget
    0.42
     Sur
    0.42
     cont
    0.41
     Cont
    0.41
    Activations Density 1.356%

    No Known Activations