© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13112
    Prev
    Next
    INDEX
    Explanations

    phrases using the word "deal", but also identifies certain words related to groups of people.

    oai_token-act-pair · gemini-2.0-flash

    "big deal" context

    np_max-act · gemini-2.0-flash

    deal

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     MonoBehaviour
    -0.67
    antart
    -0.53
     parche
    -0.51
     mús
    -0.47
     zabud
    -0.47
    gmail
    -0.46
    بوابة
    -0.45
    SerializeField
    -0.45
    DataGridView
    -0.45
     comunale
    -0.45
    POSITIVE LOGITS
    bootstrapcdn
    0.92
     AssemblyCompany
    0.91
     CreateTagHelper
    0.78
    AnchorStyles
    0.77
    -------------</
    0.76
     kasarigan
    0.71
    AddTagHelper
    0.71
     بيها
    0.69
    >//
    0.68
    QMetaType
    0.68
    Activations Density 1.244%

    No Known Activations