© 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. 12334
    Prev
    Next
    INDEX
    Explanations

    parenthetical labels, especially those with numbers or abbreviations, in scientific text with figures/tables and data analysis.

    oai_token-act-pair · gemini-2.0-flash

    terms related to data structures and programming constructs

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

    period

    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
    Бахар
    -0.45
    BuildContext
    -0.39
     history
    -0.39
     OnTrigger
    -0.39
    minyak
    -0.38
     Schatz
    -0.38
     bun
    -0.38
    ఔ
    -0.37
    ¯
    -0.37
    pytest
    -0.37
    POSITIVE LOGITS
    ParallelGroup
    0.94
    TypedDataSet
    0.79
    Geplaatst
    0.77
    SequentialGroup
    0.74
    脚注の使い方
    0.73
     мәкалә
    0.70
    хьтан
    0.68
     يتيمه
    0.66
     kaarangay
    0.65
    AndEndTag
    0.65
    Activations Density 7.374%

    No Known Activations