© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6565
    Prev
    Next
    INDEX
    Explanations

    a mix of technical language related to physics, mechanics, and human anatomy

    oai_token-act-pair · gemini-2.0-flash

    inside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     otomatig
    -0.82
     Theſe
    -0.74
    tonode
    -0.74
     AssemblyCompany
    -0.73
    queryInterface
    -0.71
     ब्रेकडाउन
    -0.70
    featureID
    -0.68
    ChildIndex
    -0.68
     AssemblyVersion
    -0.67
     themſelves
    -0.67
    POSITIVE LOGITS
     inside
    0.96
     into
    0.85
    inside
    0.83
    Inside
    0.77
     INSIDE
    0.75
     Inside
    0.73
     beneath
    0.72
     INTO
    0.71
    into
    0.69
     deep
    0.68
    Activations Density 1.576%

    No Known Activations