© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6284
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms, possibly Javascript

    oai_token-act-pair · gemini-2.0-flash

    lo

    np_max-act · gemini-2.0-flash

    Spanish function words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nakalista
    -0.88
     greateſt
    -0.80
     pleaſure
    -0.80
     poffe
    -0.79
     itſelf
    -0.78
     myſelf
    -0.78
     تانيه
    -0.77
     Anſ
    -0.76
     enfans
    -0.74
     himſelf
    -0.73
    POSITIVE LOGITS
     en
    0.52
    ,
    0.51
     que
    0.50
     EN
    0.49
     so
    0.47
    Staying
    0.47
     تج
    0.47
    Ĝ
    0.46
    knecht
    0.46
     willst
    0.45
    Activations Density 0.274%

    No Known Activations