© 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. 11122
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, scientific studies, geographical location or experimental procedures, i.e. finding proper nouns.

    oai_token-act-pair · 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
    WebVitals
    -0.57
    HideFlags
    -0.52
     transfieras
    -0.47
     financiero
    -0.46
     guz
    -0.46
    RTLE
    -0.44
    ждествен
    -0.44
     drep
    -0.44
    mtrl
    -0.43
     Achter
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.80
    Diweddarwch
    0.62
    >-->
    0.62
     enfans
    0.62
    addPreferredGap
    0.60
     [''],
    0.57
     Autorizaciones
    0.56
    tellations
    0.55
    conclusion
    0.54
    //
    0.54
    Activations Density 2.094%

    No Known Activations