© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4735
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas containing superscripts and subscripts

    oai_token-act-pair · gemini-2.0-flash

    mathematical symbols and notation

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

    mathematical notation

    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
    imarães
    -0.57
     ExecuteAsync
    -0.56
     VIAF
    -0.54
    ArgsConstructor
    -0.53
     الحره
    -0.52
     ligiloj
    -0.51
    msgSender
    -0.51
    ismet
    -0.49
    Hozzáférés
    -0.49
    buttonBar
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.95
    IsContent
    0.59
    Tracce
    0.56
     raiſ
    0.56
    generated
    0.54
     Sra
    0.53
     Jamestown
    0.52
     seh
    0.52
     Spisak
    0.52
    الحياه
    0.51
    Activations Density 6.819%

    No Known Activations