© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13004
    Prev
    Next
    INDEX
    Explanations

    words related to publications, studies, and observations

    oai_token-act-pair · gemini-2.0-flash

    observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    WindowConstants
    -0.65
    ioutil
    -0.55
    ErrorListener
    -0.54
     PLWABN
    -0.51
      
    -0.51
    tagHelperRunner
    -0.50
     /(\
    -0.50
    janos
    -0.50
    zaam
    -0.49
    toBeTruthy
    -0.49
    POSITIVE LOGITS
     Metropolitana
    0.67
    manteau
    0.63
     of
    0.61
     ocu
    0.60
    ebvre
    0.59
    <%
    0.59
    agisse
    0.59
     tiet
    0.58
     refusé
    0.57
    üttel
    0.57
    Activations Density 4.250%

    No Known Activations