© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12587
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatments and conditions, especially within the context of clinical trials and pharmaceutical interventions

    oai_token-act-pair · gemini-2.0-flash

    drugs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ########.
    -0.71
    loài
    -0.68
     EdgeInsets
    -0.64
    >{@
    -0.60
    CloseOperation
    -0.60
     المعيارى
    -0.60
    IBOutlet
    -0.59
    EndContext
    -0.58
     erfaren
    -0.56
     aanwezig
    -0.56
    POSITIVE LOGITS
    ropol
    0.46
    featureID
    0.46
    usercontent
    0.45
     NCS
    0.45
    remel
    0.43
    IsMutable
    0.43
    znam
    0.43
    βο
    0.43
     JSTOR
    0.42
    acebook
    0.42
    Activations Density 8.105%

    No Known Activations