© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12799
    Prev
    Next
    INDEX
    Explanations

    financial and media company names, often Canadian.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للاسماء
    -0.72
     betweenstory
    -0.67
    DockStyle
    -0.67
     religieuses
    -0.66
     tartalomajánló
    -0.63
     Roskov
    -0.62
    RenderAtEndOf
    -0.61
    awtextra
    -0.59
     المعيارى
    -0.59
    DeleteBehavior
    -0.59
    POSITIVE LOGITS
    enzo
    0.54
     Shaw
    0.52
     Cor
    0.52
    chach
    0.49
     Wikipédia
    0.47
    Shaw
    0.46
    бри
    0.46
    Calla
    0.46
    coup
    0.46
     T
    0.45
    Activations Density 1.546%

    No Known Activations