© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12454
    Prev
    Next
    INDEX
    Explanations

    sentences discussing the chemical composition of minerals and the processes used to extract them

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or module names

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

    minerals and ores

    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
    beton
    -0.47
     kapcsol
    -0.47
     krav
    -0.47
     dentaire
    -0.46
     vastaan
    -0.45
     larmes
    -0.44
    quir
    -0.43
    Wr
    -0.43
    defaultProps
    -0.42
     túnel
    -0.42
    POSITIVE LOGITS
     NgModule
    0.65
     otomatig
    0.62
     phase
    0.62
    ularia
    0.62
     mergeFrom
    0.60
    تقاوى
    0.57
     Al
    0.56
    expandindo
    0.56
    GEBURTSDATUM
    0.56
     AssemblyTitle
    0.56
    Activations Density 2.626%

    No Known Activations