© 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. 4622
    Prev
    Next
    INDEX
    Explanations

    instances of the word "embed" or related mathematical terms.

    oai_token-act-pair · gemini-2.0-flash

    eds

    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
    AndroidJUnit
    -0.73
     يتيمه
    -0.69
     Nauk
    -0.65
     @"/
    -0.63
    ValueStyle
    -0.63
    Personendaten
    -0.60
    UVWXYZ
    -0.59
    AddTagHelper
    -0.59
    iotensin
    -0.59
    nocache
    -0.57
    POSITIVE LOGITS
     into
    0.79
     Into
    0.74
    VideoCapture
    0.73
     INTO
    0.72
     Integrate
    0.71
    ">//
    0.70
     incorpor
    0.69
    Into
    0.68
     embed
    0.66
     embedded
    0.64
    Activations Density 2.316%

    No Known Activations