© 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. 15211
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies and propaganda, with a particular sensitivity to negative stereotypes and historical references

    oai_token-act-pair · gemini-2.0-flash

    Political entities/figures/events

    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
     Wikimedijinoj
    -0.69
     Paglinawan
    -0.65
    contentLoaded
    -0.63
    хьтан
    -0.61
     Efq
    -0.60
     densely
    -0.59
    centes
    -0.59
     préc
    -0.59
     تبد
    -0.59
    CodeAttribute
    -0.58
    POSITIVE LOGITS
     lack
    0.65
     sto
    0.61
     en
    0.56
     aco
    0.55
    cheer
    0.53
     apolog
    0.50
     cheer
    0.50
     apo
    0.47
    ঐ
    0.46
     falta
    0.44
    Activations Density 1.680%

    No Known Activations