© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13283
    Prev
    Next
    INDEX
    Explanations

    the start and end of coding namespace declarations, and function declarations

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    straints
    -0.61
     <",
    -0.59
     estekak
    -0.59
    endenza
    -0.57
    __':
    -0.57
    WebControls
    -0.56
    دانشنامهٔ
    -0.56
    avit
    -0.54
    gnition
    -0.54
    __":
    -0.54
    POSITIVE LOGITS
    
    0.64
     itſelf
    0.58
     Theſe
    0.52
     himſelf
    0.49
     ſche
    0.46
     comunale
    0.46
     CHECKBOX
    0.46
     Monfieur
    0.45
     ſch
    0.44
     yourselves
    0.43
    Activations Density 0.227%

    No Known Activations