© 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. 5136
    Prev
    Next
    INDEX
    Explanations

    code snippets, mathematical equations in LaTeX format, database queries, and structured data representations

    oai_token-act-pair · gemini-2.0-flash

    code syntax and formatting

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

    code snippets

    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
     ejus
    -0.67
     negru
    -0.63
     Leurs
    -0.63
     Egli
    -0.63
     Leur
    -0.63
     griega
    -0.63
     aveug
    -0.61
     Arki
    -0.59
     sandero
    -0.59
     Pingback
    -0.59
    POSITIVE LOGITS
    — 
    0.81
    ::~
    0.66
    onViewCreated
    0.65
    anthemum
    0.64
    ratulations
    0.64
    CppMethod
    0.61
    FTFY
    0.60
     SwitchCompat
    0.60
    蒻
    0.59
    -------
    0.57
    Activations Density 3.544%

    No Known Activations