© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10486
    Prev
    Next
    INDEX
    Explanations

    the "text-align" property in CSS

    oai_token-act-pair · gemini-2.0-flash

    align

    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
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.91
     <<<<<<<<<<<<<<
    -0.82
     []:
    -0.74
    }{*}{
    -0.73
    align
    -0.66
    fromnode
    -0.66
    setof
    -0.62
     estekak
    -0.61
     insuffisamment
    -0.61
    tetlen
    -0.60
    POSITIVE LOGITS
     CascadeType
    0.50
    By
    0.48
     cellpadding
    0.47
     washed
    0.45
    Op
    0.45
    openzeppelin
    0.44
    top
    0.44
     firebaseConfig
    0.44
     Wash
    0.43
     Sent
    0.43
    Activations Density 0.282%

    No Known Activations