© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10966
    Prev
    Next
    INDEX
    Explanations

    code snippets displaying an error message using the words maven and java in Japanese

    oai_token-act-pair · gemini-2.0-flash

    Code and errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +#+#
    -1.07
    بوابة
    -1.05
     cherchés
    -0.88
     Roskov
    -0.82
    ंदीखरीदारी
    -0.82
    ValueStyle
    -0.82
     سكانية
    -0.79
    تقاوى
    -0.78
     MainAxisSize
    -0.77
    الحياه
    -0.77
    POSITIVE LOGITS
     men
    0.51
     
    0.46
     self
    0.44
    writeInt
    0.43
     ID
    0.43
     agency
    0.42
    ?
    0.42
     true
    0.41
     error
    0.41
     false
    0.40
    Activations Density 2.512%

    No Known Activations