© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    turns of phrase that indicate the author is making a point or expressing a opinion

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

    np_token-act-pair-logits · gpt-4o-mini
    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
    twimg
    -0.52
     Wraith
    -0.44
    brido
    -0.43
    作
    -0.43
    ⇑
    -0.43
    org
    -0.42
     thinking
    -0.42
    redit
    -0.42
    res
    -0.41
     Escolar
    -0.41
    POSITIVE LOGITS
    RegistryLite
    0.80
    queryInterface
    0.73
    WaitGroup
    0.73
    ‌است
    0.73
    TypedDataSet
    0.71
    ✨:
    0.71
    yntaxException
    0.69
     فريبيس
    0.69
    setVerticalGroup
    0.68
    
    0.68
    Activations Density 6.967%

    No Known Activations