© 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. 4631
    Prev
    Next
    INDEX
    Explanations

    python code syntax and libraries

    oai_token-act-pair · gemini-2.0-flash

    programming terminology

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

    Python import statements

    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
    featureID
    -0.66
    GetKeyDown
    -0.61
    colgroup
    -0.57
     uska
    -0.54
    ])));
    -0.54
    DataPropertyName
    -0.53
    ;#
    -0.53
    SpringBootTest
    -0.52
    Gön
    -0.51
    TypedDataSet
    -0.51
    POSITIVE LOGITS
    sprechend
    0.52
     Réponses
    0.49
    culosis
    0.48
     makeStyles
    0.47
     Infect
    0.45
     censura
    0.45
     Kine
    0.44
     démission
    0.42
    TAWA
    0.42
    donc
    0.42
    Activations Density 1.649%

    No Known Activations