© 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. 10946
    Prev
    Next
    INDEX
    Explanations

    the word "highlight" and words associated with research studies

    oai_token-act-pair · gemini-2.0-flash

    highlight

    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
     
    -0.94
     '
    -0.80
     (
    -0.79
    <eos>
    -0.77
    ...
    -0.76
        
    -0.75
     "
    -0.75
    "
    -0.73
     R
    -0.73
    ↵
    -0.71
    POSITIVE LOGITS
     Monfieur
    1.35
     imprimée
    1.30
     itſelf
    1.27
     vectorielles
    1.26
     auroit
    1.24
     Efq
    1.24
     feroit
    1.20
     myſelf
    1.20
     ainfi
    1.18
     pouvoit
    1.18
    Activations Density 1.120%

    No Known Activations