© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2724
    Prev
    Next
    INDEX
    Explanations

    the word "once" and somewhat random related words that appear alongside it

    oai_token-act-pair · gemini-2.0-flash

    once

    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
     once
    -2.47
    once
    -2.09
    Once
    -1.94
     Once
    -1.86
     ONCE
    -1.68
    ONCE
    -1.56
    <bos>
    -1.08
     einmal
    -0.98
     مرة
    -0.98
    一旦
    -0.90
    POSITIVE LOGITS
     дописавши
    0.75
     onOptions
    0.68
    SBATCH
    0.66
    NUMX
    0.65
     Signalez
    0.65
    ChildScrollView
    0.65
    OrNil
    0.64
     handleMessage
    0.64
    存于互联网档案馆
    0.64
    interopRequire
    0.62
    Activations Density 7.901%

    No Known Activations