© 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. 5972
    Prev
    Next
    INDEX
    Explanations

    instances of auxiliary verbs such as "can", "could", "needs" and "should"

    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
     purpoſe
    -1.47
     Efq
    -1.45
     Jefus
    -1.41
     houſe
    -1.34
     faſt
    -1.30
     pleaſure
    -1.30
     ſtate
    -1.30
     Monfieur
    -1.30
     auffi
    -1.29
     Diſ
    -1.29
    POSITIVE LOGITS
    ↵↵
    1.10
     
    0.90
    <bos>
    0.79
    '
    0.73
    ↵
    0.70
     I
    0.67
    .
    0.66
     N
    0.63
    ’
    0.61
    N
    0.59
    Activations Density 3.752%

    No Known Activations