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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8220
    Prev
    Next
    INDEX
    Explanations

    the word "accordingly" and nearby legal or official information

    oai_token-act-pair · gemini-2.0-flash

    accordingly

    np_max-act · gemini-2.0-flash
    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
    ↵
    -1.33
      
    -1.18
     
    -1.11
    ↵↵
    -1.05
    '
    -1.02
    ’
    -1.02
     "
    -1.02
     “
    -1.01
    The
    -0.96
    <eos>
    -0.93
    POSITIVE LOGITS
     myſelf
    1.62
     Мексичка
    1.62
     auroit
    1.60
     feroit
    1.59
     ſeveral
    1.58
     ainfi
    1.56
     doubtnut
    1.55
     Monfieur
    1.53
     Efq
    1.53
     avoient
    1.52
    Activations Density 1.281%

    No Known Activations