© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6537
    Prev
    Next
    INDEX
    Explanations

    words in a historical context that describe what countries and people want, intend, or are compelled to do

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     StringTokenizer
    -0.68
    RegressionTest
    -0.66
     ***!
    -0.62
    expandindo
    -0.61
    HtmlAttribute
    -0.61
     cucchiai
    -0.60
     kaarangay
    -0.59
     Италијани
    -0.59
    addCriterion
    -0.59
    tvguidetime
    -0.57
    POSITIVE LOGITS
    VIAF
    0.54
    viron
    0.52
     Weltkrieg
    0.52
    balleur
    0.51
     MonoBehaviour
    0.49
    ismen
    0.48
    linge
    0.48
    crose
    0.48
    berge
    0.47
    eavor
    0.47
    Activations Density 3.985%

    No Known Activations