© 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. 9582
    Prev
    Next
    INDEX
    Explanations

    social media links and discussions of Venezuelan politics

    oai_token-act-pair · gemini-2.0-flash

    Political discussions/news

    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
     Patil
    -0.56
    urtstag
    -0.53
     المعيارى
    -0.52
    Попис
    -0.51
    getMinutes
    -0.51
    колеп
    -0.50
    quité
    -0.50
     minut
    -0.50
     secrete
    -0.49
     financeira
    -0.49
    POSITIVE LOGITS
    UserScript
    0.74
    >(&
    0.54
    liffe
    0.52
     Veel
    0.48
     opposition
    0.48
    Opposition
    0.47
     Opposition
    0.46
     hyper
    0.45
     useRouter
    0.45
     Borel
    0.44
    Activations Density 1.185%

    No Known Activations