© 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. 5430
    Prev
    Next
    INDEX
    Explanations

    questions asking "why" or "would."

    oai_token-act-pair · gemini-2.0-flash

    would

    np_max-act · gemini-2.0-flash
    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
    estars
    -0.66
     onAnimation
    -0.57
     المعيارى
    -0.57
     Affiliations
    -0.56
    omial
    -0.52
    dő
    -0.52
    ⎩
    -0.51
    Terr
    -0.51
    "—
    -0.49
    γου
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.77
    intios
    0.68
     autorytatywna
    0.65
    Билгалдахарш
    0.63
     Vikipedi
    0.61
     kasarigan
    0.60
    Derbyniad
    0.59
    mergeFrom
    0.58
    Искәрмәләр
    0.57
    yntaxException
    0.57
    Activations Density 1.464%

    No Known Activations