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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10226
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "chapter"

    oai_token-act-pair · gemini-2.0-flash

    cha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.17
    ↵
    -1.17
      
    -1.09
       
    -1.05
        
    -0.93
     (
    -0.91
     _
    -0.86
         
    -0.84
    x
    -0.83
    s
    -0.81
    POSITIVE LOGITS
     ſind
    1.79
     Efq
    1.77
     photolibrary
    1.77
     myſelf
    1.72
     itſelf
    1.69
     doubtnut
    1.67
     $_(
    1.66
    脚注の使い方
    1.62
     Jefus
    1.59
     ་་
    1.59
    Activations Density 1.078%

    No Known Activations