© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11292
    Prev
    Next
    INDEX
    Explanations

    the `sizeof` operator (used in C/C++ to determine the size of a data type)

    oai_token-act-pair · gemini-2.0-flash

    sizeof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     sizeof
    -1.08
    sizeof
    -1.06
     שוליים
    -1.02
    Personendaten
    -0.88
    });*/
    -0.88
    DebuggerNonUser
    -0.84
    MLLoader
    -0.82
     Chwiliwch
    -0.80
     оригіналу
    -0.80
     CreateTagHelper
    -0.80
    POSITIVE LOGITS
    <bos>
    0.87
    '
    0.62
    ’
    0.50
    (
    0.47
    $
    0.47
    owicz
    0.46
    vikle
    0.45
    ov
    0.45
    -
    0.45
    __((
    0.44
    Activations Density 0.212%

    No Known Activations