© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10335
    Prev
    Next
    INDEX
    Explanations

    a mixture of financial jargon and event attendance

    oai_token-act-pair · gemini-2.0-flash

    sold out or short positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     surla
    -0.70
     modelAndView
    -0.61
     pulang
    -0.57
    roj
    -0.57
    mism
    -0.55
     MonoBehaviour
    -0.54
    ederos
    -0.53
    ập
    -0.53
    leck
    -0.53
     ब्रेकडाउन
    -0.52
    POSITIVE LOGITS
     चीज़ों
    0.49
    IsMutable
    0.48
    WriteBarrier
    0.48
     AssemblyVersion
    0.47
    المناصب
    0.46
    EndInit
    0.45
    ynı
    0.45
     cosa
    0.45
    ModelSerializer
    0.45
    CloseOperation
    0.45
    Activations Density 1.787%

    No Known Activations