© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11078
    Prev
    Next
    INDEX
    Explanations

    words related to conducting scientific analysis or related statistical observations of data

    oai_token-act-pair · gemini-2.0-flash

    analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    XmlAccessorType
    -0.79
    oredCriteria
    -0.78
    neſs
    -0.76
    UserScript
    -0.76
    Hentet
    -0.75
    contentLoaded
    -0.74
     otomatig
    -0.74
    cèse
    -0.73
    PreferredItem
    -0.71
    PMailer
    -0.71
    POSITIVE LOGITS
     of
    0.55
    اتر
    0.51
    Extensions
    0.45
     and
    0.43
     od
    0.41
    richt
    0.40
    Inc
    0.39
    .
    0.38
    를
    0.38
    czy
    0.38
    Activations Density 7.191%

    No Known Activations