© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12233
    Prev
    Next
    INDEX
    Explanations

    section headers with the surrounding punctuation in study documentation

    oai_token-act-pair · gemini-2.0-flash

    Technical research 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
    peño
    -0.57
    ruppe
    -0.56
     putty
    -0.55
    uesday
    -0.55
    исленность
    -0.53
    hama
    -0.50
    sunter
    -0.50
    IRQn
    -0.50
     BATCH
    -0.50
    ars
    -0.49
    POSITIVE LOGITS
    findpost
    0.74
     tartalomajánló
    0.70
     المعيارى
    0.66
    Попис
    0.66
    fromnode
    0.61
    География
    0.59
    ///</
    0.59
    adpleegd
    0.54
    :✨
    0.54
     LoggerFactory
    0.52
    Activations Density 0.960%

    No Known Activations