© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15584
    Prev
    Next
    INDEX
    Explanations

    discourse markers, conjunctions, references, and other words and punctuation used to structure arguments or present related notions within a discussion.

    oai_token-act-pair · gemini-2.0-flash

    text blending technical and legal terminology

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -0.72
    webElementGuid
    -0.70
    sidemargin
    -0.65
     كومونز
    -0.64
    EndGlobalSection
    -0.64
    SharedDtor
    -0.64
    Datuak
    -0.60
    abestanden
    -0.59
    HasAnnotation
    -0.58
    Chham
    -0.57
    POSITIVE LOGITS
    ########.
    0.64
     aufzu
    0.59
     campan
    0.53
    berfläche
    0.48
    createCell
    0.48
     Ferner
    0.47
    ('.');
    0.45
    umpul
    0.45
    addChild
    0.44
    दान
    0.44
    Activations Density 0.564%

    No Known Activations