© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3876
    Prev
    Next
    INDEX
    Explanations

    words related to code and windows-style interfaces

    oai_token-act-pair · gemini-2.0-flash

    mentions of "Rich" or related terms

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

    rich text

    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
     Мексичка
    -0.56
     torchvision
    -0.56
    apimachinery
    -0.53
    IntoConstraints
    -0.52
     AssemblyVersion
    -0.52
     purpoſe
    -0.52
     handleMessage
    -0.51
    GraphicsUnit
    -0.50
    بوابة
    -0.50
    VideoCapture
    -0.50
    POSITIVE LOGITS
     Rich
    0.84
    Rich
    0.81
     rich
    0.79
    tin
    0.65
     CK
    0.64
    富
    0.64
    rich
    0.64
     editor
    0.63
     wy
    0.59
     Tiny
    0.59
    Activations Density 2.009%

    No Known Activations