© 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. 5232
    Prev
    Next
    INDEX
    Explanations

    German articles `der`, `die`, `das`, `ein`, and `einen` or English articles `a`, `an`, and `the`

    oai_token-act-pair · gemini-2.0-flash

    der

    np_max-act · gemini-2.0-flash

    Der

    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
    expandindo
    -1.08
     виправивши
    -1.08
     ivelany
    -1.04
    +#+#
    -1.02
     المعيارى
    -0.96
    InjectAttribute
    -0.91
    ReusableCell
    -0.88
    RenderAtEndOf
    -0.86
     snippetHide
    -0.85
     propOrder
    -0.84
    POSITIVE LOGITS
    <bos>
    0.91
     the
    0.72
     a
    0.69
     an
    0.67
    “
    0.56
     con
    0.56
     
    0.55
     is
    0.55
    ,
    0.54
    "
    0.54
    Activations Density 2.210%

    No Known Activations