© 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. 4619
    Prev
    Next
    INDEX
    Explanations

    mentions of "child" or "children," especially in a programming context

    oai_token-act-pair · gemini-2.0-flash

    child processes in code

    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
     posthum
    -0.56
    Provider
    -0.48
     BoxFit
    -0.47
     vitro
    -0.47
     Suff
    -0.46
    תיים
    -0.46
    нутри
    -0.45
    ?
    -0.45
     split
    -0.44
    iso
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.76
    ConstraintMaker
    0.71
    MigrationBuilder
    0.71
     estekak
    0.68
    rungsseite
    0.66
    UserScript
    0.65
     smtplib
    0.62
    ]")]
    0.62
    ultier
    0.61
    EndContext
    0.61
    Activations Density 0.070%

    No Known Activations