© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12507
    Prev
    Next
    INDEX
    Explanations

    words referring to mechanical components and fasteners, especially electrical-related ones.

    oai_token-act-pair · gemini-2.0-flash

    Inventions descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ltä
    -0.64
     elä
    -0.56
     vetorial
    -0.56
     Campaigns
    -0.55
     myö
    -0.54
     aikaa
    -0.53
     esportivo
    -0.52
     dře
    -0.52
     florales
    -0.51
     ģ
    -0.51
    POSITIVE LOGITS
    TagMode
    0.87
    TintMode
    0.80
    EndGlobalSection
    0.79
     autorytatywna
    0.78
    Personendaten
    0.74
    IUrlHelper
    0.74
    +#+#
    0.72
     himo
    0.70
    verwijspagina
    0.69
    RegressionTest
    0.69
    Activations Density 3.994%

    No Known Activations