© 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. 14398
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers and statistics

    oai_token-act-pair · gemini-2.0-flash

    amounts and quantities

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

    million

    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
    ✨:
    -0.56
    addCriterion
    -0.56
    featureID
    -0.55
    InstrumentedTest
    -0.52
    DebuggerStep
    -0.52
     ajuta
    -0.52
     Bourgoin
    -0.51
    oredCriteria
    -0.51
     encuent
    -0.51
    ingale
    -0.50
    POSITIVE LOGITS
     words
    0.55
     letters
    0.53
     two
    0.52
     new
    0.52
     pieces
    0.48
     visitors
    0.48
     answers
    0.48
    TextWatcher
    0.47
     customers
    0.47
    zeczy
    0.47
    Activations Density 6.231%

    No Known Activations