© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9452
    Prev
    Next
    INDEX
    Explanations

    phrases about people working together

    oai_token-act-pair · gemini-2.0-flash

    closely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    HostException
    -0.71
     plough
    -0.71
     ploughing
    -0.70
    enumii
    -0.69
     Encyclopædia
    -0.68
     Encyclopaedia
    -0.67
    $^\
    -0.66
    IntoConstraints
    -0.65
     $_"
    -0.65
     Kuj
    -0.64
    POSITIVE LOGITS
    <bos>
    0.57
    Odkazy
    0.46
    TagMode
    0.44
    قایناق‌لار
    0.43
     اك
    0.40
    kezett
    0.40
    锈钢
    0.40
     уси
    0.40
    JsonHelper
    0.40
    addView
    0.39
    Activations Density 1.851%

    No Known Activations