© 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. 2601
    Prev
    Next
    INDEX
    Explanations

    question and answer forum related language like questions, answers, and gratitude or appreciation

    oai_token-act-pair · gemini-2.0-flash

    words and phrases indicating questions or requests for advice

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

    Q&A ending with thanks

    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
     EventEmitter
    -0.47
    dataTables
    -0.43
    l
    -0.42
     kali
    -0.41
    ukt
    -0.41
     setuptools
    -0.41
     eslint
    -0.41
    izzle
    -0.40
    verige
    -0.40
    wrappers
    -0.39
    POSITIVE LOGITS
    IsMutable
    0.74
     للاسماء
    0.73
     autorytatywna
    0.71
     Any
    0.66
     NSCoder
    0.65
     وتسجيلات
    0.65
    RegressionTest
    0.64
    Portály
    0.64
    WriteTagHelper
    0.64
     Thanks
    0.63
    Activations Density 3.678%

    No Known Activations