© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10543
    Prev
    Next
    INDEX
    Explanations

    generally negative political rhetoric concerning laws, government, and reform.

    oai_token-act-pair · gemini-2.0-flash

    politics

    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
     <=",
    -0.84
     defStyleAttr
    -0.72
     ویکی‌آمباردا
    -0.70
     <",
    -0.69
    Nuorodos
    -0.68
     meriva
    -0.67
    ']>;
    -0.66
    '])){
    -0.66
     NSCoder
    -0.65
    ")){
    -0.64
    POSITIVE LOGITS
     fair
    0.48
    aimerais
    0.47
     CÁ
    0.46
     koo
    0.45
    thos
    0.44
     common
    0.44
    common
    0.42
     Rest
    0.41
     retrou
    0.40
     Vali
    0.40
    Activations Density 2.002%

    No Known Activations