© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12643
    Prev
    Next
    INDEX
    Explanations

    code snippets with XML-like syntax, application and website information as well as HTML code

    oai_token-act-pair · gemini-2.0-flash

    XML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Snape
    -0.45
    圏
    -0.44
     sija
    -0.43
     nosotros
    -0.42
     noastre
    -0.41
    <b>
    -0.41
     Nosotros
    -0.41
    ânea
    -0.41
     alimentaire
    -0.41
     österreich
    -0.41
    POSITIVE LOGITS
     resourceCulture
    1.08
    windowFixed
    1.01
    UnusedPrivate
    0.97
    DebuggerNonUser
    0.91
     snippetHide
    0.90
    NameInMap
    0.86
     وتسجيلات
    0.85
    تقاوى
    0.85
     kaarangay
    0.84
    دانشنامهٔ
    0.82
    Activations Density 6.705%

    No Known Activations