© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16268
    Prev
    Next
    INDEX
    Explanations

    general words that tend to be used in writing, such as articles and short verbs

    oai_token-act-pair · gemini-2.0-flash

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     мәкал
    -0.71
    ScopeManager
    -0.71
    tagHelperRunner
    -0.67
     himo
    -0.66
    kháu
    -0.66
    談社
    -0.65
    ArrowToggle
    -0.65
     ब्रेकडाउन
    -0.64
    HandlerContext
    -0.63
    Παραπομπές
    -0.63
    POSITIVE LOGITS
    рованной
    0.45
     int
    0.45
    ровали
    0.44
     directed
    0.44
     %@",
    0.44
    %@",
    0.43
    ıllı
    0.42
     criminal
    0.41
    dinger
    0.41
     hitting
    0.40
    Activations Density 5.428%

    No Known Activations