© 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. 14468
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to file handling and error management

    oai_token-act-pair · gemini-2.0-flash

    specific programming or technical terms

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

    code

    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
     espirituales
    -0.52
    gymn
    -0.51
    Chham
    -0.50
     seleção
    -0.49
     juridique
    -0.49
     rând
    -0.47
    capace
    -0.46
     duy
    -0.46
     líqu
    -0.46
     religione
    -0.45
    POSITIVE LOGITS
     esternos
    0.73
    tanleria
    0.69
     referenties
    0.66
    цезда
    0.65
    ArrowToggle
    0.62
     estekak
    0.62
    IsContent
    0.59
     Administrativna
    0.58
     Мексичка
    0.57
     AspNetCore
    0.56
    Activations Density 4.785%

    No Known Activations