© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8355
    Prev
    Next
    INDEX
    Explanations

    code-related terms and keywords, especially variable names, parameters, and color/temperature references.

    oai_token-act-pair · gemini-2.0-flash

    Color

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    fromnode
    -0.57
     TextInputType
    -0.50
    теризу
    -0.48
    INITY
    -0.44
    TypeError
    -0.44
    worldly
    -0.43
    ]+=
    -0.43
    rrggbb
    -0.43
     gawas
    -0.43
    einander
    -0.42
    POSITIVE LOGITS
     ***!
    0.69
     linkovi
    0.68
    Parcelize
    0.67
     vedea
    0.59
    קישורים
    0.56
    RunAsync
    0.56
    matchCondition
    0.56
     isComment
    0.55
     Socialista
    0.54
     is
    0.54
    Activations Density 1.678%

    No Known Activations