© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9223
    Prev
    Next
    INDEX
    Explanations

    varied terms, sometimes related to application development and sometimes to other topics like history, but with a slightly negative connotation based on the surrounding words.

    oai_token-act-pair · gemini-2.0-flash

    programming/technical details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     greateſt
    -0.65
     Wikimedijinoj
    -0.65
     noastră
    -0.65
     umani
    -0.62
    ']))
    -0.61
    )):
    -0.60
     JADX
    -0.60
     nécessairement
    -0.60
     umana
    -0.58
     leçons
    -0.58
    POSITIVE LOGITS
     EconPapers
    0.62
    TagMode
    0.61
     dispon
    0.59
    rungsseite
    0.58
    DockStyle
    0.57
     utafitiHapana
    0.56
    Nowadays
    0.52
     Nowadays
    0.52
     Reverso
    0.51
    Lenght
    0.49
    Activations Density 4.712%

    No Known Activations