© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5425
    Prev
    Next
    INDEX
    Explanations

    LaTeX or other mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    specific formatting or special characters

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

    $}

    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
    MLLoader
    -1.10
    BeginContext
    -0.85
    InstanceState
    -0.82
    oneofs
    -0.78
    transQ
    -0.71
    OGND
    -0.71
    :✨
    -0.69
     isInitialized
    -0.67
    AndEndTag
    -0.65
    AddTagHelper
    -0.64
    POSITIVE LOGITS
    nbsp
    0.45
    солю
    0.44
     hold
    0.42
     Mittel
    0.41
    fah
    0.41
     घट
    0.41
     finish
    0.41
     finished
    0.40
    endl
    0.40
     walk
    0.40
    Activations Density 5.463%

    No Known Activations