© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11115
    Prev
    Next
    INDEX
    Explanations

    discussions of monetary topics like taxes, revenue, and avoiding costs

    oai_token-act-pair · gemini-2.0-flash

    Taxes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     końcu
    -0.57
     disambiguazione
    -0.57
    renderItem
    -0.57
     végétale
    -0.56
     déchir
    -0.56
    MessageOf
    -0.56
    addCriterion
    -0.56
    HideFlags
    -0.55
     OnInit
    -0.54
     économiques
    -0.54
    POSITIVE LOGITS
    存于互联网档案馆
    0.54
     Italijani
    0.45
     فريبيس
    0.45
    InvalidProtocol
    0.43
    SharedDtor
    0.41
    Спољашње
    0.40
    Rhestr
    0.40
     catch
    0.39
    AppRoutingModule
    0.39
     omnia
    0.39
    Activations Density 1.186%

    No Known Activations