© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9804
    Prev
    Next
    INDEX
    Explanations

    code snippets or code-related terms

    oai_token-act-pair · gemini-2.0-flash

    Code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Worse
    -0.61
     Missed
    -0.58
     Protecting
    -0.58
     Achieving
    -0.56
     Absolutely
    -0.56
     Toward
    -0.56
    athione
    -0.55
     Respect
    -0.55
     Preventing
    -0.55
     Afford
    -0.54
    POSITIVE LOGITS
    GroupLayout
    0.81
     CreateTagHelper
    0.76
    XmlAccessType
    0.75
     GenerationType
    0.72
    ⓧ
    0.69
    invokeLater
    0.68
     defaultstate
    0.68
     convertView
    0.68
    SQLiteDatabase
    0.68
    FunctionFlags
    0.68
    Activations Density 25.079%

    No Known Activations