© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11102
    Prev
    Next
    INDEX
    Explanations

    terms related to silicon and chemical elements, often in the context of scientific or technical discussions.

    oai_token-act-pair · gemini-2.0-flash

    si

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Si
    -1.59
     Si
    -1.53
     si
    -1.47
    si
    -1.41
    SI
    -1.31
     SI
    -1.27
     Си
    -0.79
    sy
    -0.73
    sip
    -0.73
     sy
    -0.71
    POSITIVE LOGITS
     تضيفلها
    0.86
     propOrder
    0.84
    GEBURTSDATUM
    0.77
    ReusableCell
    0.75
     Савезне
    0.73
     autorytatywna
    0.73
    хьтан
    0.73
     otomatig
    0.69
    zzar
    0.68
     ſta
    0.68
    Activations Density 8.990%

    No Known Activations