© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13091
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like "to be" and "to have."

    oai_token-act-pair · gemini-2.0-flash

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    expandindo
    -0.82
    ThroughAttribute
    -0.79
     typelib
    -0.78
     Normdatei
    -0.75
    RenderAtEndOf
    -0.73
     AssemblyProduct
    -0.70
    Население
    -0.69
    Demografie
    -0.69
     GenerationType
    -0.69
    UnsafeEnabled
    -0.67
    POSITIVE LOGITS
     board
    0.46
    board
    0.42
     innamor
    0.41
     maît
    0.41
     boards
    0.40
    bu
    0.40
     cú
    0.40
    कार
    0.40
    char
    0.39
     bero
    0.39
    Activations Density 2.313%

    No Known Activations