© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6181
    Prev
    Next
    INDEX
    Explanations

    discussions of problems and solutions regarding energy companies and policies

    oai_token-act-pair · gemini-2.0-flash

    specific proper nouns or terms

    np_token-act-pair-logits · gpt-4o-mini

    Organizations and issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     doInBackground
    -0.68
     الحره
    -0.63
     Erişim
    -0.62
    الحياه
    -0.57
     Zacks
    -0.56
    IInterface
    -0.54
    
    -0.53
    GNUC
    -0.53
    Zacks
    -0.52
     MainAxisSize
    -0.52
    POSITIVE LOGITS
     TextInputType
    0.57
    empereur
    0.52
    Angleterre
    0.51
    RDP
    0.48
    Empereur
    0.48
    deck
    0.47
    oa̍t
    0.47
    Tembelea
    0.47
     gmin
    0.47
     Lambeth
    0.45
    Activations Density 2.914%

    No Known Activations