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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15411
    Prev
    Next
    INDEX
    Explanations

    words associated with an organization, especially in the context of seeking permission or dealing with authorities

    oai_token-act-pair · gemini-2.0-flash

    Scientology and legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    LookAnd
    -0.67
    IndentedString
    -0.64
     gynhyrchwyd
    -0.63
    Vidite
    -0.60
    RegressionTest
    -0.58
    WebVitals
    -0.57
     MonoBehaviour
    -0.56
    offsetof
    -0.56
     fieldNum
    -0.54
     चीज़ों
    -0.52
    POSITIVE LOGITS
     mieux
    0.71
    før
    0.62
    /**
    0.60
     self
    0.58
     Paul
    0.57
    rasti
    0.54
    ",$
    0.54
    olis
    0.53
     God
    0.53
    hana
    0.52
    Activations Density 7.442%

    No Known Activations