© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3084
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets for array manipulation, focusing on comparisons, loops, and conditional statements, potentially within the context of calculating a median.

    oai_token-act-pair · gemini-2.0-flash

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    writeFieldEnd
    -0.63
    <!--
    -0.59
    تفصیلات
    -0.58
    )_/¯
    -0.57
    archiviato
    -0.56
    nofollow
    -0.56
    ::$_
    -0.54
    idł
    -0.54
    EndContext
    -0.53
    colgroup
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.62
    SharedCtor
    0.56
    مصادر
    0.53
     &___
    0.53
     disponibilités
    0.49
    Carriera
    0.48
    didSet
    0.46
    BeginContext
    0.46
    Raw
    0.45
     Kog
    0.45
    Activations Density 0.167%

    No Known Activations