© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10547
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even" followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    even

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     even
    -3.80
    even
    -3.34
    Even
    -2.88
     Even
    -2.86
     EVEN
    -2.69
     даже
    -2.61
     même
    -2.45
     навіть
    -2.44
     incluso
    -2.39
     nawet
    -2.39
    POSITIVE LOGITS
     nahilalakip
    0.85
    Geplaatst
    0.85
    ThroughAttribute
    0.85
     Normdatei
    0.84
    parsedMessage
    0.83
    TagMode
    0.82
     незавершена
    0.82
     CURIAM
    0.79
    EndContext
    0.78
    
    0.76
    Activations Density 0.726%

    No Known Activations