© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10121
    Prev
    Next
    INDEX
    Explanations

    source code or structured data, possibly with a focus on error messages or protocols

    oai_token-act-pair · gemini-2.0-flash

    parsed messages in different languages

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

    say 2

    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
     Zidane
    -0.54
    <tfoot>
    -0.54
     Bondi
    -0.53
    inheritdoc
    -0.52
     Tind
    -0.51
    magnetism
    -0.51
     GMT
    -0.50
    getSystemService
    -0.49
    一动
    -0.49
     III
    -0.49
    POSITIVE LOGITS
    parsedMessage
    0.82
    ագրություններ
    0.70
    הערות
    0.59
    Šaltiniai
    0.57
     préoccup
    0.57
     vicenda
    0.56
     dúvidas
    0.55
     }{@
    0.52
     doute
    0.51
    KURZBESCHREIBUNG
    0.50
    Activations Density 7.629%

    No Known Activations