© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5742
    Prev
    Next
    INDEX
    Explanations

    scientific vocabulary, especially in the fields of medicine, chemistry, and mathematics.

    oai_token-act-pair · gemini-2.0-flash

    say "▁" Method used: 2 — tokens after tend to start with ▁, so say "▁"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Dryer
    -0.71
     Aluno
    -0.69
    BottomSheet
    -0.68
    aris
    -0.66
     estratégico
    -0.65
     gius
    -0.63
    skr
    -0.63
    MySql
    -0.63
     apparente
    -0.63
     ErrorCode
    -0.61
    POSITIVE LOGITS
    /−
    1.16
    >>>>>>>>
    1.09
     Houſe
    0.93
     estekak
    0.90
    InjectAttribute
    0.88
    awtextra
    0.86
     Jefus
    0.86
    PyTuple
    0.83
    shutil
    0.82
     itſelf
    0.81
    Activations Density 18.937%

    No Known Activations