© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 11011
    Prev
    Next
    INDEX
    Explanations

    language related to business processes, especially accounting and surveys

    oai_token-act-pair · gemini-2.0-flash

    Documents, requests, information

    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
    الحياه
    -0.81
    Jeografia
    -0.77
     المعيارى
    -0.71
     invokingState
    -0.69
    TagMode
    -0.67
    oa̍t
    -0.66
    клопе
    -0.65
    ⓧ
    -0.64
     Савезне
    -0.64
    
    -0.64
    POSITIVE LOGITS
    ']);
    
    0.65
    '])->
    0.57
    '],$
    0.54
    XDECREF
    0.53
    ']){
    0.52
    ']));
    0.51
    "]];
    0.49
     GenerationType
    0.48
    '];
    
    0.48
    )._
    0.48
    Activations Density 2.522%

    No Known Activations