© 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. 13573
    Prev
    Next
    INDEX
    Explanations

    phrases implying a challenge or confrontation directed at an audience

    oai_token-act-pair · 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
     الحره
    -0.67
    rungsseite
    -0.58
    assium
    -0.57
    CloseOperation
    -0.56
    onomía
    -0.55
    RenderAtEndOf
    -0.55
     partout
    -0.54
    XtraBars
    -0.54
     ListTile
    -0.54
     فريبيس
    -0.54
    POSITIVE LOGITS
     invokingState
    0.51
     forget
    0.51
     fine
    0.50
    Tough
    0.49
    RefNanny
    0.48
    tough
    0.48
     createContext
    0.48
     Вікіпе
    0.48
    AndroidJUnit
    0.48
    thâu
    0.48
    Activations Density 0.747%

    No Known Activations