© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4196
    Prev
    Next
    INDEX
    Explanations

    colons or words related to ethnicity or style / names of months

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act · gemini-2.0-flash

    say "▁" Method used: 2 — tokens start with ▁

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     jadx
    -0.57
    DebuggerNonUser
    -0.55
     Laus
    -0.54
    CppMethod
    -0.53
    InSection
    -0.52
     Theodo
    -0.48
     sporo
    -0.48
    sizeCache
    -0.48
    tact
    -0.47
     tev
    -0.47
    POSITIVE LOGITS
    <bos>
    0.79
     autorytatywna
    0.63
    orianCalendar
    0.62
     scolaires
    0.60
    Parcelize
    0.55
    chauer
    0.55
    AddHtmlAttribute
    0.54
    bilden
    0.54
     ведь
    0.53
     canadienne
    0.53
    Activations Density 0.589%

    No Known Activations