© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4106
    Prev
    Next
    INDEX
    Explanations

    quotes, especially single quotes, and words that proceed or surround them

    oai_token-act-pair · gemini-2.0-flash

    single quotes

    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
     Efq
    -1.75
     Theſe
    -1.48
     itſelf
    -1.46
     myſelf
    -1.42
     Monfieur
    -1.26
     auffi
    -1.23
     himſelf
    -1.21
     raiſ
    -1.20
     becauſe
    -1.20
     Jefus
    -1.19
    POSITIVE LOGITS
    <eos>
    0.77
    ...
    0.74
    ↵↵↵
    0.73
     ‘
    0.73
     
    0.72
     [
    0.71
     (
    0.70
    </i>
    0.69
     “
    0.68
     w
    0.67
    Activations Density 0.393%

    No Known Activations