© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    code snippets and SQL queries, particularly those including '$sql', 'query', and 'prepare'.

    oai_token-act-pair · gemini-2.0-flash

    SQL related terms

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

    Source code

    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
    abetes
    -0.48
     drinkers
    -0.47
    médiaire
    -0.45
     Artifact
    -0.41
    motherapy
    -0.41
    Embeddable
    -0.40
     singleton
    -0.40
     चाहिए
    -0.40
    mirante
    -0.40
     resistor
    -0.40
    POSITIVE LOGITS
    
    0.79
    niająca
    0.75
    Personendaten
    0.73
    Datuak
    0.69
     betweenstory
    0.67
    Spoljašnje
    0.65
     ComVisible
    0.63
    ſelves
    0.62
     iſt
    0.62
    --$
    0.61
    Activations Density 0.230%

    No Known Activations