© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13224
    Prev
    Next
    INDEX
    Explanations

    legal citations, currency amounts and other numbers shown with punctuation

    oai_token-act-pair · gemini-2.0-flash

    technical terminology or code snippets

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

    Citations

    np_max-act-logits · gemini-2.0-flash

    ▁

    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_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
    asInstanceOf
    -0.51
     Schlacht
    -0.50
    seamnă
    -0.47
     ""))
    -0.47
    ‌اند
    -0.46
    resents
    -0.45
    kusi
    -0.44
    눠
    -0.44
     ')[
    -0.44
    popper
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.93
     مرئيه
    0.90
     متعلقه
    0.90
    aarrggbb
    0.84
    enterOuterAlt
    0.82
    WebVitals
    0.81
    AnchorStyles
    0.79
    
    0.78
     Normdatei
    0.77
    MethodManager
    0.77
    Activations Density 2.217%

    No Known Activations