© 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. 5066
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions

    oai_token-act-pair · gemini-2.0-flash

    abbreviations related to grading systems

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

    parentheses and ampersands

    np_max-act-logits · gemini-2.0-flash

    say "all caps abbreviations" Method used: 2 — because following tokens are uppercase acronyms — say "all caps abbreviations"

    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
    UnsafeEnabled
    -0.63
    cookieParser
    -0.60
    .")
    -0.60
     GenerationType
    -0.60
     GMC
    -0.59
     Glan
    -0.58
     g
    -0.57
     GK
    -0.57
     GOO
    -0.57
     GS
    -0.56
    POSITIVE LOGITS
    PMG
    0.89
    MG
    0.85
     AG
    0.83
     EG
    0.82
     mg
    0.82
     MG
    0.82
    mg
    0.81
     NG
    0.81
    EG
    0.81
    NG
    0.81
    Activations Density 1.590%

    No Known Activations