© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12756
    Prev
    Next
    INDEX
    Explanations

    code and variable names in computer programs

    oai_token-act-pair · gemini-2.0-flash

    code/math notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    msgSender
    -0.52
     por
    -0.49
     (
    -0.48
     G
    -0.47
     j
    -0.46
     plus
    -0.46
     Le
    -0.45
     J
    -0.45
     of
    -0.44
    PerPage
    -0.43
    POSITIVE LOGITS
    expandindo
    1.09
     bezeichneter
    0.90
     Anſ
    0.79
    новништво
    0.78
    InjectAttribute
    0.78
     wikipagina
    0.76
    SequentialGroup
    0.76
    ьаж
    0.74
    ⓧ
    0.74
     Shakspeare
    0.73
    Activations Density 2.949%

    No Known Activations