© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14755
    Prev
    Next
    INDEX
    Explanations

    code snippets containing file paths and function calls

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming code

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

    code and programming

    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
     שוליים
    -0.69
    falen
    -0.50
    angsaan
    -0.48
     виправивши
    -0.47
     चुनें
    -0.47
     myś
    -0.47
    CodedInputStream
    -0.47
    |<\
    -0.47
     "--
    -0.47
    endio
    -0.47
    POSITIVE LOGITS
    новниш
    0.60
    RetentionPolicy
    0.58
     المعيارى
    0.52
     kasarigan
    0.52
     Expanded
    0.49
    styleType
    0.48
     expansion
    0.48
    expanded
    0.47
     tree
    0.46
    Искәрмәләр
    0.46
    Activations Density 4.236%

    No Known Activations