© 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. 12214
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a sentiment or reaction

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    Negative Logits
    הערות
    -0.64
    DeclareMath
    -0.57
     ExecuteAsync
    -0.55
    $
    -0.52
    structs
    -0.52
    TestingModule
    -0.49
    roffen
    -0.49
    WebServlet
    -0.47
    Congrats
    -0.47
    posedge
    -0.47
    POSITIVE LOGITS
    :✨
    0.76
     Administrativna
    0.71
    AndroidJUnit
    0.69
     kasarigan
    0.59
    InitVars
    0.58
     demografica
    0.57
    يكب
    0.57
    DataAnnotations
    0.54
    GEBURTSDATUM
    0.54
     Panasonic
    0.54
    Activations Density 5.162%

    No Known Activations