© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5344
    Prev
    Next
    INDEX
    Explanations

    the word "that"

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act · gemini-2.0-flash

    that

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -0.72
     
    -0.67
     one
    -0.63
     previous
    -0.61
    ↵↵
    -0.60
     most
    -0.60
     very
    -0.59
     so
    -0.55
     case
    -0.55
    <blockquote>
    -0.54
    POSITIVE LOGITS
    setVerticalGroup
    0.74
    PerformLayout
    0.74
    ?")
    0.71
    ?')
    0.70
     Forder
    0.67
    PreferredItem
    0.66
     ―――
    0.64
    ."]
    0.64
    ?");
    0.63
     لينك
    0.63
    Activations Density 0.664%

    No Known Activations