© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13791
    Prev
    Next
    INDEX
    Explanations

    the word "at", especially when following the word "look"

    oai_token-act-pair · gemini-2.0-flash

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     unavailable
    -0.54
    Év
    -0.54
     bibl
    -0.53
    ませて
    -0.52
    ませ
    -0.52
     junior
    -0.52
    saturated
    -0.52
    lai
    -0.52
    hmen
    -0.51
    躇
    -0.51
    POSITIVE LOGITS
    <bos>
    1.06
    MigrationBuilder
    0.87
    AddTagHelper
    0.86
    queryInterface
    0.81
     /\.
    0.81
     transfieras
    0.79
    Portail
    0.76
    makeConstraints
    0.75
    
    0.73
    awtextra
    0.72
    Activations Density 0.366%

    No Known Activations