© 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. 2659
    Prev
    Next
    INDEX
    Explanations

    code snippets related to URL routing

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code annotations

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

    code paths/URLs

    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
    contentLoaded
    -0.69
     arşivlendi
    -0.54
     mxArray
    -0.50
    Kapcsolódó
    -0.48
    dropIfExists
    -0.47
     vaut
    -0.46
    SystemColors
    -0.45
     Gabel
    -0.45
     iconFacebook
    -0.44
    OuterClass
    -0.44
    POSITIVE LOGITS
    참고
    0.68
    تقاوى
    0.65
     NgModule
    0.65
    脚注の使い方
    0.63
     HasFactory
    0.61
    UserScript
    0.58
     CURIAM
    0.56
    enumerable
    0.54
     estimés
    0.54
    存于互联网档案馆
    0.54
    Activations Density 2.615%

    No Known Activations