© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10477
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the structure and function of neural networks, especially those involving numerical data processing and hidden layers

    oai_token-act-pair · gemini-2.0-flash

    mean, hidden layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    cepti
    -0.54
    Gran
    -0.52
    pau
    -0.52
     Harsh
    -0.51
    occup
    -0.51
     Gran
    -0.51
    ousel
    -0.50
    UnknownFieldSet
    -0.50
     Hard
    -0.50
    Carriera
    -0.50
    POSITIVE LOGITS
     Administrativna
    0.59
    extAlignment
    0.58
    +#+#
    0.57
    RegressionTest
    0.56
     AssemblyVersion
    0.55
     متعلقه
    0.54
     >=",
    0.52
    HomeAsUpEnabled
    0.52
    ----</
    0.52
    তথ্যসূত্র
    0.52
    Activations Density 3.310%

    No Known Activations