© 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. 8051
    Prev
    Next
    INDEX
    Explanations

    the word "build" and its synonyms, as well as words frequently found nearby.

    oai_token-act-pair · gemini-2.0-flash

    words related to building and improvement

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

    build

    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
    ngdoc
    -0.57
    Datuak
    -0.56
    minecraftforge
    -0.54
    featureID
    -0.53
     ویکی‌پدیای
    -0.52
    eventbus
    -0.52
    ServletRequest
    -0.51
     Оно
    -0.50
     finanzas
    -0.48
    hacer
    -0.48
    POSITIVE LOGITS
     a
    0.76
     meaningful
    0.63
    isContained
    0.61
     healthy
    0.61
    ')")
    0.60
     an
    0.60
    ParallelGroup
    0.60
    fillType
    0.59
     strong
    0.56
     walls
    0.56
    Activations Density 2.586%

    No Known Activations