© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11573
    Prev
    Next
    INDEX
    Explanations

    words associated with desire and intent.

    oai_token-act-pair · gemini-2.0-flash

    want

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Šaltiniai
    -0.64
    WillAppear
    -0.62
    esModule
    -0.60
     ویکی‌پدیا
    -0.60
    WebVitals
    -0.60
     JpaRepository
    -0.59
    İstinadlar
    -0.59
     Вікі
    -0.57
    UrlResolution
    -0.53
     RoutedEventArgs
    -0.52
    POSITIVE LOGITS
     there
    0.51
     auditors
    0.51
    more
    0.51
    support
    0.48
     swimmers
    0.48
    readers
    0.48
     fellow
    0.47
    Rohy
    0.47
     more
    0.47
     soar
    0.47
    Activations Density 6.248%

    No Known Activations