© 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. 11909
    Prev
    Next
    INDEX
    Explanations

    the letters "au"

    oai_token-act-pair · gemini-2.0-flash

    au

    np_max-act · gemini-2.0-flash

    au

    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_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
     ECB
    -0.88
     ESE
    -0.84
     StatelessWidget
    -0.84
    EDEFAULT
    -0.81
     gainera
    -0.81
     Libri
    -0.79
     AVC
    -0.79
     Plaster
    -0.78
     Audubon
    -0.78
     AVA
    -0.77
    POSITIVE LOGITS
    <bos>
    1.91
     the
    0.79
    '
    0.72
     
    0.62
     this
    0.59
    ’
    0.57
     a
    0.57
     his
    0.56
     my
    0.54
     he
    0.53
    Activations Density 2.937%

    No Known Activations