© 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. 6738
    Prev
    Next
    INDEX
    Explanations

    the word "undefined."

    oai_token-act-pair · gemini-2.0-flash

    undefined

    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
     étoient
    -1.08
    berdayakan
    -1.07
     feroit
    -0.97
     avoient
    -0.91
     Majefty
    -0.90
     ―――――
    -0.90
    ########.
    -0.88
     eenige
    -0.87
     auroit
    -0.86
     étoit
    -0.85
    POSITIVE LOGITS
     I
    0.80
     
    0.73
    <eos>
    0.67
     A
    0.66
    ↵↵
    0.64
     As
    0.63
     In
    0.61
     Will
    0.61
     R
    0.61
      
    0.61
    Activations Density 0.659%

    No Known Activations