© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12943
    Prev
    Next
    INDEX
    Explanations

    uses of conjunctions and abbreviations

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.67
    NameInMap
    -0.58
     localObject
    -0.56
    expandindo
    -0.56
     olds
    -0.52
     Estar
    -0.52
    GHIJKLM
    -0.52
    protoimpl
    -0.52
    raciones
    -0.51
     Magist
    -0.51
    POSITIVE LOGITS
    AnchorStyles
    0.64
    bootstrapcdn
    0.62
    TagMode
    0.55
    adpleegd
    0.54
    }{*}{
    0.54
     insuffisamment
    0.48
    HttpFoundation
    0.46
    الإنجليزية
    0.46
    lapsed
    0.45
     viaggi
    0.44
    Activations Density 12.657%

    No Known Activations