© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6493
    Prev
    Next
    INDEX
    Explanations

    the auxiliary verbs may, shall, could, and did

    oai_token-act-pair · gemini-2.0-flash

    modal verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.58
     Anſ
    -1.58
     Reſ
    -1.57
     greateſt
    -1.54
     Diſ
    -1.48
     iſt
    -1.48
     ―――――
    -1.45
     Houſe
    -1.45
     Majefty
    -1.42
     Monfieur
    -1.42
    POSITIVE LOGITS
    '
    1.09
    ↵
    1.06
    ↵↵
    0.94
    .
    0.93
    ’
    0.88
    -
    0.82
     
    0.82
    ,
    0.81
    <bos>
    0.77
     A
    0.72
    Activations Density 0.304%

    No Known Activations