© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13542
    Prev
    Next
    INDEX
    Explanations

    words related to SQL, databases and programming languages

    oai_token-act-pair · gemini-2.0-flash

    SQL databases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ăzi
    -0.45
    inheritdoc
    -0.44
    cox
    -0.43
    曜日
    -0.42
     MainAxisSize
    -0.40
    zeile
    -0.40
     life
    -0.40
     Shetty
    -0.38
     retention
    -0.38
     reten
    -0.37
    POSITIVE LOGITS
    protoimpl
    0.80
    ValueStyle
    0.78
    BagConstraints
    0.75
    MethodManager
    0.69
    enderror
    0.68
     صوتيه
    0.67
    findpost
    0.67
    sizeCache
    0.66
    ⓧ
    0.65
     Roskov
    0.64
    Activations Density 21.100%

    No Known Activations