© 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. 1431
    Prev
    Next
    INDEX
    Explanations

    years in the 1900s, especially the decades ending in '0'

    oai_token-act-pair · gemini-2.0-flash

    s

    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
    <bos>
    -0.77
     chỗ
    -0.54
    struktion
    -0.52
     normaux
    -0.52
    ientôt
    -0.52
    стракт
    -0.52
    idora
    -0.50
     conversión
    -0.49
    WithError
    -0.49
     simplicité
    -0.49
    POSITIVE LOGITS
    ChildScrollView
    0.78
    IVEREF
    0.77
    AsUp
    0.71
    ✭✭
    0.63
    makeText
    0.62
    клопе
    0.58
     Alembic
    0.58
     AssemblyCompany
    0.57
    KEYCODE
    0.57
    medriver
    0.56
    Activations Density 1.999%

    No Known Activations