© 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. 15360
    Prev
    Next
    INDEX
    Explanations

    articles about the Chinese Communist Party

    oai_token-act-pair · gemini-2.0-flash

    political parties and leaders

    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
    rungsseite
    -0.86
    .*")]
    -0.69
    twimg
    -0.54
    geen
    -0.50
     Agree
    -0.49
     oblige
    -0.49
    場合があります
    -0.48
     Treat
    -0.47
    mai
    -0.47
    Tre
    -0.47
    POSITIVE LOGITS
     surla
    0.53
    Geschäfts
    0.51
    InjectAttribute
    0.50
    FOOTNOTES
    0.49
     invokingState
    0.49
     Rami
    0.49
    DebuggerNonUser
    0.48
    xmlns
    0.47
    bux
    0.47
    Tazama
    0.46
    Activations Density 0.433%

    No Known Activations