© 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. 9782
    Prev
    Next
    INDEX
    Explanations

    the word "want" followed by "to"

    oai_token-act-pair · gemini-2.0-flash

    want

    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
    تقاوى
    -0.93
     дописавши
    -0.84
    MLLoader
    -0.84
     ProtoMessage
    -0.81
     ویکی‌پدی
    -0.76
    ArrowToggle
    -0.75
     Италијани
    -0.75
    Personensuche
    -0.75
    PerformLayout
    -0.75
     ITIS
    -0.75
    POSITIVE LOGITS
    <bos>
    0.46
    زة
    0.45
     WebElement
    0.44
    之力
    0.42
    gled
    0.42
    lar
    0.41
     link
    0.40
     Guar
    0.40
     offering
    0.39
     hasard
    0.39
    Activations Density 0.247%

    No Known Activations