© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14315
    Prev
    Next
    INDEX
    Explanations

    HTML code related to font awesome icons being used to display plus or minus signs

    oai_token-act-pair · gemini-2.0-flash

    code-related terminology

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

    code/programming

    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
    Not in Any Lists

    No Comments

    Negative Logits
     transférez
    -0.63
    IVEREF
    -0.58
    awtextra
    -0.56
    ContentLoaded
    -0.50
    VOID
    -0.50
    @__
    -0.49
     createState
    -0.49
     jLabel
    -0.48
     вікі
    -0.48
     indépendante
    -0.48
    POSITIVE LOGITS
    AnchorStyles
    0.66
    expandindo
    0.60
    kels
    0.57
     Reverso
    0.54
     TRAP
    0.52
    HtmlAttribute
    0.51
    slidesToShow
    0.50
    rrggbb
    0.50
    tuur
    0.49
    outState
    0.49
    Activations Density 0.982%

    No Known Activations