© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12370
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating medical procedures, tests, and equipment, especially in the context of doctor interactions and prescriptions.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    }');
    -0.69
     ModelExpression
    -0.66
     تانيه
    -0.66
     HttpNotFound
    -0.64
    principalColumn
    -0.64
    مصادر
    -0.63
     Normdatei
    -0.63
     jScrollPane
    -0.60
     ujednoznacz
    -0.59
    })*/
    -0.59
    POSITIVE LOGITS
    AlterField
    0.60
    UserScript
    0.48
    RemoveField
    0.45
     nocturna
    0.45
     propOrder
    0.44
    AddField
    0.44
    calaure
    0.44
    Newswire
    0.43
    投
    0.42
    Aktualisiert
    0.42
    Activations Density 4.058%

    No Known Activations