© 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. 11671
    Prev
    Next
    INDEX
    Explanations

    Java code syntax, especially method calls and class references

    oai_token-act-pair · gemini-2.0-flash

    code syntax and structure

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

    Dot punctuation

    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
    .
    -0.76
     e
    -0.65
     u
    -0.63
     y
    -0.62
    ,
    -0.56
     s
    -0.56
     f
    -0.55
     E
    -0.54
     x
    -0.53
     q
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    1.13
     myſelf
    1.05
     itſelf
    1.05
    AndEndTag
    1.00
     ―――――
    0.97
     ་་
    0.96
    存于互联网档案馆
    0.96
    InputBorder
    0.94
    UrlResolution
    0.93
     useAppContext
    0.92
    Activations Density 0.257%

    No Known Activations