© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1630
    Prev
    Next
    INDEX
    Explanations

    parts of Java code that include "*/", "Nonnull", "Nullable", "::", or "Object."

    oai_token-act-pair · gemini-2.0-flash

    programming language keywords or functions

    np_token-act-pair-logits · gpt-4o-mini

    Code-related keywords

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    o
    -0.51
    äsentation
    -0.49
    U
    -0.47
     BorderRadius
    -0.47
    Бахар
    -0.46
    a
    -0.43
    トー
    -0.42
    t
    -0.42
    <em>
    -0.42
    c
    -0.42
    POSITIVE LOGITS
    berdayakan
    0.87
    ThroughAttribute
    0.87
    RegressionTest
    0.85
    contentLoaded
    0.70
    tinyos
    0.69
     intptr
    0.68
     nakalista
    0.65
     disambiguazione
    0.63
     CreateTagHelper
    0.63
     bezeichneter
    0.63
    Activations Density 2.161%

    No Known Activations