© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4282
    Prev
    Next
    INDEX
    Explanations

    addresses and locations in Oregon

    oai_token-act-pair · gemini-2.0-flash

    programming keywords or syntax strings

    np_token-act-pair-logits · gpt-4o-mini

    Code-related tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     pstmt
    -0.39
     sanitarias
    -0.38
     cardiaque
    -0.37
     teor
    -0.36
     adsorbed
    -0.35
     figlio
    -0.34
     segnal
    -0.34
     ovat
    -0.34
     држа
    -0.34
    錨
    -0.34
    POSITIVE LOGITS
     defaultstate
    0.81
    rungsseite
    0.79
    MENAFN
    0.75
     MainAxisSize
    0.75
    ########.
    0.73
    DispatchToProps
    0.73
     CreateTagHelper
    0.70
    
    0.69
     protoimpl
    0.69
    DoubleQuotes
    0.68
    Activations Density 0.680%

    No Known Activations