© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11216
    Prev
    Next
    INDEX
    Explanations

    words from multiple romance languages related to understanding, possessing, or programming.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    PRNewswire
    -0.71
    uxxxx
    -0.67
    buttonBar
    -0.65
    ########.
    -0.64
     المعيارى
    -0.63
     Administrativna
    -0.60
    WriteBarrier
    -0.58
    GraphicsUnit
    -0.58
    AlterField
    -0.57
     Antiquities
    -0.56
    POSITIVE LOGITS
     altres
    0.60
    DrawerToggle
    0.50
    ijnen
    0.48
     useContext
    0.46
     még
    0.43
     geslacht
    0.42
     trụ
    0.42
     paraît
    0.42
    gründung
    0.40
    tigny
    0.40
    Activations Density 0.405%

    No Known Activations