© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6075
    Prev
    Next
    INDEX
    Explanations

    code-related terms, particularly function definitions and configuration

    oai_token-act-pair · gemini-2.0-flash

    Programming 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_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
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.79
     itſelf
    -0.68
     ―――――
    -0.68
    RegressionTest
    -0.61
     سكانية
    -0.58
    ChildScrollView
    -0.57
     myſelf
    -0.56
     Monfieur
    -0.56
    发表于
    -0.56
     Italijanski
    -0.54
    POSITIVE LOGITS
    SBATCH
    0.54
     ProtoMessage
    0.51
    interopRequire
    0.51
     do
    0.46
     os
    0.46
     remplacement
    0.45
    makedirs
    0.45
     red
    0.45
     assist
    0.44
    internalType
    0.44
    Activations Density 9.952%

    No Known Activations