© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2458
    Prev
    Next
    INDEX
    Explanations

    medical terms, especially related to pain management, medication, and addiction.

    oai_token-act-pair · gemini-2.0-flash

    terms related to opioid treatments

    np_token-act-pair-logits · gpt-4o-mini

    Drug addiction treatment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     HasFactory
    -0.65
     MainAxisSize
    -0.64
    detectChanges
    -0.62
    SBATCH
    -0.60
     useParams
    -0.56
     indisponible
    -0.52
     '\\;'
    -0.52
    DoubleQuotes
    -0.52
     sumpay
    -0.52
    Referanser
    -0.51
    POSITIVE LOGITS
     code
    0.56
     Paglinawan
    0.54
    ########.
    0.54
     Op
    0.54
    éras
    0.52
    ⓧ
    0.49
    HasAnnotation
    0.49
    caris
    0.48
    Op
    0.48
    offsetof
    0.48
    Activations Density 0.706%

    No Known Activations