© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11587
    Prev
    Next
    INDEX
    Explanations

    java or kotlin code

    oai_token-act-pair · gemini-2.0-flash

    code-related terms or patterns

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

    void

    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
     ejus
    -0.54
     SOF
    -0.51
     quæ
    -0.51
     LTS
    -0.49
    式
    -0.48
     Reps
    -0.47
     buoni
    -0.46
     noastre
    -0.46
     doré
    -0.45
     coleg
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.97
    fromnode
    0.79
     AssemblyCulture
    0.75
    енча
    0.74
     لينك
    0.71
     Roskov
    0.69
    énario
    0.69
     noDo
    0.68
    PropertyChanging
    0.67
    Fazit
    0.66
    Activations Density 1.045%

    No Known Activations