© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12052
    Prev
    Next
    INDEX
    Explanations

    the word "medium" and related contextual words such as "lower" and "deep," possibly in a scientific context

    oai_token-act-pair · gemini-2.0-flash

    medium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    .
    -0.91
    ,
    -0.82
    ↵
    -0.79
    ;
    -0.71
    :
    -0.65
    !
    -0.65
    I
    -0.64
    "
    -0.63
    i
    -0.62
      
    -0.60
    POSITIVE LOGITS
    TypedDataSet
    1.27
     فريبيس
    1.25
     kaarangay
    1.25
     المعيارى
    1.22
    NUMX
    1.22
    tvguidetime
    1.18
    awtextra
    1.17
     autorytatywna
    1.15
    expandindo
    1.14
    Искәрмәләр
    1.13
    Activations Density 1.314%

    No Known Activations