© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    scientific and technical language related to models, dynamics, systems, and implementations

    oai_token-act-pair · gemini-2.0-flash

    scientific models

    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
    SequentialGroup
    -0.73
    lgari
    -0.69
     وتسجيلات
    -0.65
    findpost
    -0.63
     виправивши
    -0.63
    OGND
    -0.60
     lourd
    -0.58
     aikaa
    -0.58
    TagMode
    -0.56
     AssemblyCompany
    -0.56
    POSITIVE LOGITS
     UIApplication
    0.51
     transfer
    0.51
    interopRequire
    0.50
     Transfer
    0.49
    Comp
    0.49
    ruptedException
    0.47
    COMP
    0.47
     microscopic
    0.47
     transfers
    0.46
     Cour
    0.45
    Activations Density 4.306%

    No Known Activations