© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9044
    Prev
    Next
    INDEX
    Explanations

    statements that are philosophical musings on marriage, religion, and justice

    oai_token-act-pair · gemini-2.0-flash

    "end" or "means"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     незавершена
    -0.65
    
    -0.57
     переписи
    -0.56
     fieldNum
    -0.53
     فريبيس
    -0.50
    TestingModule
    -0.49
    elemField
    -0.48
     Signalez
    -0.48
    ểu
    -0.47
    出版年
    -0.47
    POSITIVE LOGITS
     ends
    1.14
     Ends
    0.98
     end
    0.94
    ends
    0.94
     ENDS
    0.85
    Ends
    0.81
    End
    0.81
     End
    0.78
    Means
    0.77
     END
    0.69
    Activations Density 0.726%

    No Known Activations