© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12353
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to car engines and transmissions

    oai_token-act-pair · gemini-2.0-flash

    non-English words or symbols

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

    engine/clutch

    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
    WebElementEntity
    -0.47
    getReference
    -0.47
     che
    -0.45
    eleste
    -0.45
     tim
    -0.42
     tee
    -0.41
     Den
    -0.41
     mer
    -0.41
     extra
    -0.41
    otor
    -0.41
    POSITIVE LOGITS
     rospy
    0.66
    ]--;
    0.60
    saraba
    0.60
    脚注の使い方
    0.60
    Izvori
    0.60
    ruptedException
    0.60
     blest
    0.59
     Offisielt
    0.58
     Giugno
    0.57
     Houſe
    0.56
    Activations Density 0.580%

    No Known Activations