© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8006
    Prev
    Next
    INDEX
    Explanations

    text discussing education and fake news

    oai_token-act-pair · gemini-2.0-flash

    school education

    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
     himſelf
    -0.82
     Monfieur
    -0.81
     Majefty
    -0.77
     themſelves
    -0.77
     whoſe
    -0.76
     Efq
    -0.76
     itſelf
    -0.75
     myſelf
    -0.75
     pleaſure
    -0.74
     Jefus
    -0.73
    POSITIVE LOGITS
     uska
    0.44
    ècie
    0.42
    chart
    0.42
    Jeografia
    0.41
     use
    0.41
    minecraft
    0.41
    scss
    0.40
     ré
    0.40
    APIView
    0.40
    Switch
    0.40
    Activations Density 10.187%

    No Known Activations