© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13184
    Prev
    Next
    INDEX
    Explanations

    words related to abstract concepts that are often nouns formed from regular verbs

    oai_token-act-pair · 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
    ismet
    -0.45
     ویکی‌پدیای
    -0.38
    Rade
    -0.35
     diferencial
    -0.35
    ViewFeatures
    -0.34
     Plant
    -0.34
     pamamagitan
    -0.34
     riego
    -0.34
     suya
    -0.33
    
    -0.33
    POSITIVE LOGITS
    UnusedPrivate
    0.79
    VersionUID
    0.79
    WarningLevel
    0.78
    XmlAccessorType
    0.71
    /*
    0.69
    省市镇
    0.68
    ousands
    0.68
    MessageState
    0.68
    ècie
    0.68
     Italijani
    0.67
    Activations Density 1.684%

    No Known Activations