© 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. 15830
    Prev
    Next
    INDEX
    Explanations

    instances of words being used to describe advice or ways of doing things

    oai_token-act-pair · gemini-2.0-flash

    first element of lists

    np_max-act-logits · 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
    liš
    -0.49
    Round
    -0.43
     most
    -0.43
    omitempty
    -0.42
    CO
    -0.42
    apin
    -0.42
    EventHandler
    -0.42
     Round
    -0.42
    ชาย
    -0.42
     sapere
    -0.41
    POSITIVE LOGITS
    HasForeignKey
    0.80
     propOrder
    0.74
    bootstrapcdn
    0.72
    RectangleBorder
    0.70
    RenderAtEndOf
    0.69
    Portail
    0.68
    pexpr
    0.68
    AsUp
    0.68
    MLLoader
    0.67
     onAnimation
    0.67
    Activations Density 1.503%

    No Known Activations