© 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. 12127
    Prev
    Next
    INDEX
    Explanations

    what appears to be URLs, filenames, and code snippets

    oai_token-act-pair · gemini-2.0-flash

    tokens related to references and citations

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

    Figures and references

    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
    parsedMessage
    -1.17
     مشين
    -1.07
     متعلقه
    -1.01
    writeFieldEnd
    -1.01
     Roskov
    -0.94
     ModelExpression
    -0.93
    fromnode
    -0.93
    Izvori
    -0.90
     gradova
    -0.90
    twimg
    -0.89
    POSITIVE LOGITS
    a
    0.78
    b
    0.69
    .
    0.52
    A
    0.50
     b
    0.49
    i
    0.49
    c
    0.48
    e
    0.46
    ↵
    0.46
    k
    0.45
    Activations Density 5.976%

    No Known Activations