© 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. 5814
    Prev
    Next
    INDEX
    Explanations

    legal code references and the word "motion"

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act · gemini-2.0-flash

    function words

    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
     avoient
    -1.44
     feroit
    -1.40
     vectorielles
    -1.40
     Theſe
    -1.37
     étoient
    -1.34
     plufieurs
    -1.34
     pouvoit
    -1.30
     auroit
    -1.29
     chré
    -1.27
     cérami
    -1.27
    POSITIVE LOGITS
     
    1.00
     the
    0.97
    ing
    0.96
    ↵↵
    0.84
     a
    0.79
    <eos>
    0.78
      
    0.77
     In
    0.75
     “
    0.70
     C
    0.69
    Activations Density 2.415%

    No Known Activations