© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6640
    Prev
    Next
    INDEX
    Explanations

    words starting with "nano"

    oai_token-act-pair · gemini-2.0-flash

    nan

    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
     
    -0.81
     The
    -0.69
    ↵↵
    -0.68
    '];?>
    -0.66
    ↵↵↵
    -0.63
    <bos>
    -0.60
     Di
    -0.56
      
    -0.56
    '])){
    -0.56
    <eos>
    -0.54
    POSITIVE LOGITS
    SequentialGroup
    1.01
     تضيفلها
    1.00
     ſmall
    0.97
     Chwiliwch
    0.97
    ValueStyle
    0.96
     متعلقه
    0.94
     pleaſure
    0.93
     purpoſe
    0.90
     reaſon
    0.87
     myſelf
    0.86
    Activations Density 1.717%

    No Known Activations