© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11069
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in technical or scientific descriptions of devices and processes

    oai_token-act-pair · gemini-2.0-flash

    items/objects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     présidenti
    -0.56
    IsMutable
    -0.51
    ThroughAttribute
    -0.48
    sidemargin
    -0.47
    :///
    -0.47
     présidentielle
    -0.47
     Gedächt
    -0.47
    avax
    -0.46
    ftagPool
    -0.46
     détach
    -0.45
    POSITIVE LOGITS
     items
    1.16
     objects
    1.08
     item
    1.05
     Items
    0.99
     Objects
    0.96
    物品
    0.96
     materials
    0.91
     oggetti
    0.91
     Item
    0.91
     products
    0.91
    Activations Density 5.776%

    No Known Activations