© 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. 12478
    Prev
    Next
    INDEX
    Explanations

    language related to the defensive capabilities of a sports team

    oai_token-act-pair · gemini-2.0-flash

    defense

    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
     Infórmanos
    -0.46
    স্ত
    -0.46
    ilige
    -0.46
    pared
    -0.41
     Interim
    -0.41
    „
    -0.40
     serie
    -0.40
    <tr>
    -0.40
    цов
    -0.40
    osom
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    1.03
     InputDecoration
    0.90
    AxisAlignment
    0.86
    localctx
    0.84
    IntoConstraints
    0.79
    expandindo
    0.78
     snippetHide
    0.77
    forChild
    0.77
    TintMode
    0.77
    存于互联网档案馆
    0.75
    Activations Density 0.781%

    No Known Activations