© 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. 15615
    Prev
    Next
    INDEX
    Explanations

    code, especially C++ or Java, with preprocessor directives and copyright notices

    oai_token-act-pair · gemini-2.0-flash

    code snippets or programming terminology

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

    Code and Licenses

    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
     ویکی‌پدیای
    -0.60
     صوتيه
    -0.59
     通販
    -0.54
     japoneses
    -0.54
     préféré
    -0.54
     mourut
    -0.53
     <",
    -0.52
     polaire
    -0.51
     giuri
    -0.51
     avoient
    -0.50
    POSITIVE LOGITS
    WebVitals
    0.58
    THISDAY
    0.55
    towns
    0.54
    spli
    0.54
     Gilles
    0.53
    SuccessListener
    0.53
    unhofer
    0.52
    ArrowToggle
    0.52
    +#+#
    0.52
    feier
    0.50
    Activations Density 0.515%

    No Known Activations