© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4684
    Prev
    Next
    INDEX
    Explanations

    XML namespace declarations, Java imports, and GUI-related keywords

    oai_token-act-pair · gemini-2.0-flash

    non-English terms or specialized vocabulary

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

    code and schemas

    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
    ret
    -0.68
     little
    -0.65
     us
    -0.65
     it
    -0.65
     and
    -0.63
     the
    -0.63
     –
    -0.63
     
    -0.63
     cur
    -0.63
    ,
    -0.63
    POSITIVE LOGITS
     Мексичка
    1.27
     فريبيس
    1.13
    WebVitals
    1.11
     ་་
    0.98
    ագրություններ
    0.98
     itſelf
    0.98
    AnimationsModule
    0.96
     Theſe
    0.96
     Shakspeare
    0.95
     يتيمه
    0.92
    Activations Density 1.986%

    No Known Activations