© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13407
    Prev
    Next
    INDEX
    Explanations

    terms related to Brazilian politics, scandals, and politicians.

    oai_token-act-pair · gemini-2.0-flash

    political figures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IsMutable
    -0.91
    rrggbb
    -0.90
    ItemBackground
    -0.85
    setVerticalGroup
    -0.83
    OCCURRED
    -0.81
     متعلقه
    -0.81
    تقاوى
    -0.81
     doubtnut
    -0.79
    Geplaatst
    -0.79
     surla
    -0.77
    POSITIVE LOGITS
     e
    0.63
     de
    0.60
     del
    0.47
     E
    0.44
     das
    0.41
     le
    0.39
     du
    0.39
     switch
    0.38
     r
    0.36
     d
    0.35
    Activations Density 0.362%

    No Known Activations