© 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. 4951
    Prev
    Next
    INDEX
    Explanations

    the word "shut" and words that express feelings

    oai_token-act-pair · gemini-2.0-flash

    shut

    np_max-act · gemini-2.0-flash

    ▁shut

    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
     ainfi
    -1.62
     enfans
    -1.45
     feroit
    -1.39
     auffi
    -1.36
     auroit
    -1.34
    ConstraintMaker
    -1.30
     avoient
    -1.28
     Monfieur
    -1.27
     plufieurs
    -1.27
     chré
    -1.26
    POSITIVE LOGITS
     
    1.02
      
    0.82
    ↵↵
    0.77
    ,
    0.77
    <blockquote>
    0.76
     is
    0.75
     “
    0.75
    ↵
    0.73
     and
    0.73
     I
    0.71
    Activations Density 1.239%

    No Known Activations