© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10417
    Prev
    Next
    INDEX
    Explanations

    electricity and circuitry terminology

    oai_token-act-pair · gemini-2.0-flash

    electrical engineering texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     NSCoder
    -0.66
    liceerd
    -0.64
     AssemblyCulture
    -0.56
    eezy
    -0.55
     Blazers
    -0.54
    apunov
    -0.54
    Referanser
    -0.53
    σθαι
    -0.52
    ANTLR
    -0.50
     sandstone
    -0.50
    POSITIVE LOGITS
     ExecuteAsync
    0.63
    ftagPool
    0.55
    Initializable
    0.52
    Bissau
    0.52
    HasOne
    0.51
    RegressionTest
    0.50
    GeoNames
    0.46
     AssemblyTitle
    0.46
     INTERESAR
    0.46
    PyExc
    0.46
    Activations Density 3.420%

    No Known Activations