© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12962
    Prev
    Next
    INDEX
    Explanations

    terms related to economic or civic government, also possibly health departments

    oai_token-act-pair · gemini-2.0-flash

    government and taxes

    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
    Geplaatst
    -0.62
     itſelf
    -0.59
    rália
    -0.59
    PORARY
    -0.58
    ".
    -0.57
     actionMode
    -0.57
     raiſ
    -0.57
     ويكيميديا
    -0.56
     Anſ
    -0.56
    campista
    -0.56
    POSITIVE LOGITS
     nahilalakip
    0.59
     فريبيس
    0.50
    횟
    0.49
    ":[{
    0.49
    UnusedPrivate
    0.47
     <>",
    0.47
     Schuld
    0.46
     Réponses
    0.46
    (
    0.44
    SharedCtor
    0.43
    Activations Density 35.185%

    No Known Activations