© 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. 7721
    Prev
    Next
    INDEX
    Explanations

    sentences regarding personal finance, investing, or stock trading

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming language concepts

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

    stock trading

    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
     juridiques
    -0.63
     BrowserModule
    -0.60
     cardiaque
    -0.55
     decorativa
    -0.55
    Demikian
    -0.53
     visuelle
    -0.52
     rentrée
    -0.51
     culturale
    -0.50
    ":"",
    -0.50
     legales
    -0.49
    POSITIVE LOGITS
    mybatisplus
    0.68
    存于互联网档案馆
    0.56
    IsContent
    0.55
    migrationBuilder
    0.55
    CPtr
    0.54
    WebVitals
    0.53
    pe
    0.50
    istoitu
    0.50
    調
    0.50
    iste
    0.49
    Activations Density 2.818%

    No Known Activations