© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7493
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions

    oai_token-act-pair · gemini-2.0-flash

    math, time, sewing, death

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    rungsseite
    -0.65
    脚注の使い方
    -0.57
    <bos>
    -0.50
    ler
    -0.45
     thất
    -0.45
    let
    -0.45
    LETS
    -0.45
    臺
    -0.45
    se
    -0.45
     برانيه
    -0.44
    POSITIVE LOGITS
    `/
    0.68
    InjectAttribute
    0.66
    sizeCache
    0.60
     and
    0.59
     ProtoMessage
    0.59
    ajuato
    0.59
    ＆
    0.59
    Autoritní
    0.58
     &
    0.57
     \&
    0.57
    Activations Density 2.165%

    No Known Activations