© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8533
    Prev
    Next
    INDEX
    Explanations

    code, equations, and output from running a program

    oai_token-act-pair · gemini-2.0-flash

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    zzlies
    -0.64
    eload
    -0.60
    ualaikum
    -0.59
    fellow
    -0.59
    daq
    -0.58
    kuuta
    -0.58
    لينا
    -0.58
    uolo
    -0.58
    REFERRED
    -0.58
    Материал
    -0.58
    POSITIVE LOGITS
    <bos>
    0.93
    '
    0.54
    "
    0.54
    enterOuterAlt
    0.52
    K
    0.48
    >+</
    0.47
    ."
    0.47
    >=</
    0.46
     afectados
    0.46
    \[
    0.45
    Activations Density 4.441%

    No Known Activations