© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5086
    Prev
    Next
    INDEX
    Explanations

    formulas and equations, especially when involving parameters, energies, and probabilities

    oai_token-act-pair · gemini-2.0-flash

    unconventional or specialized terms

    np_token-act-pair-logits · gpt-4o-mini

    is, are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Viited
    -0.59
    expandindo
    -0.58
     externi
    -0.50
     preuve
    -0.49
    editForm
    -0.47
    arrête
    -0.47
    lifying
    -0.46
    NgModule
    -0.45
    一看
    -0.45
     Hivatalos
    -0.45
    POSITIVE LOGITS
     understood
    0.62
    Nazionale
    0.59
    adaş
    0.59
     StatelessWidget
    0.59
     MainAxisSize
    0.57
    StoryboardSegue
    0.56
     <<<<<<<<<<<<<<
    0.55
    AttributeSet
    0.54
    embatan
    0.54
    يديا
    0.54
    Activations Density 3.397%

    No Known Activations