© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13548
    Prev
    Next
    INDEX
    Explanations

    numbers followed by a period

    oai_token-act-pair · gemini-2.0-flash

    arXiv papers

    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
    coltà
    -0.48
     typelib
    -0.47
    Portale
    -0.47
    ỏi
    -0.45
    idom
    -0.45
    jiny
    -0.45
    ijn
    -0.44
    achal
    -0.44
    mut
    -0.44
     BoxDecoration
    -0.43
    POSITIVE LOGITS
     désolés
    0.70
    GOTREF
    0.65
     noDo
    0.64
    ThroughAttribute
    0.63
     ſtate
    0.62
    InstrumentedTest
    0.59
     تكبرها
    0.58
    richTextPanel
    0.57
    tersebut
    0.56
    Carcinogenicity
    0.55
    Activations Density 2.076%

    No Known Activations