© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9279
    Prev
    Next
    INDEX
    Explanations

    words expressing gratitude and blessings

    oai_token-act-pair · gemini-2.0-flash

    tokens related to programming and functions or inputs

    np_token-act-pair-logits · gpt-4o-mini

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    noscript
    -0.53
    IContainer
    -0.51
    specialchars
    -0.49
     Reverso
    -0.49
    didSet
    -0.49
     kuid
    -0.46
    modelBuilder
    -0.46
     vis
    -0.46
    หวัด
    -0.46
    例文
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
    GEBURTSDATUM
    0.67
     cherchés
    0.65
     defaultstate
    0.65
     חיצוניים
    0.63
    IUrlHelper
    0.62
    oredCriteria
    0.62
     quoi
    0.60
     cliquant
    0.58
     greateſt
    0.54
    Activations Density 0.651%

    No Known Activations