© 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. 420
    Prev
    Next
    INDEX
    Explanations

    the word "just" and the word "to" nearby in the text

    oai_token-act-pair · 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
    enterOuterAlt
    -0.96
     MainAxisSize
    -0.84
     ModelExpression
    -0.84
     myſelf
    -0.82
    ArrowToggle
    -0.82
     Himo
    -0.78
     Efq
    -0.75
    CppMethod
    -0.72
    Obrázky
    -0.71
    Datuak
    -0.71
    POSITIVE LOGITS
    ůli
    0.46
     bet
    0.45
    nola
    0.43
     n
    0.42
     ver
    0.42
     ध
    0.41
     E
    0.41
    ulink
    0.40
     Mer
    0.40
     op
    0.40
    Activations Density 1.098%

    No Known Activations