© 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. 6171
    Prev
    Next
    INDEX
    Explanations

    the fragment "ag"

    oai_token-act-pair · gemini-2.0-flash

    ag

    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
     ag
    -1.34
    ag
    -1.10
     Ag
    -1.08
    Ag
    -0.86
     AG
    -0.85
    AG
    -0.78
     en
    -0.75
     […]
    -0.66
    agin
    -0.63
    </i>
    -0.63
    POSITIVE LOGITS
     religieuses
    0.98
     Monfieur
    0.97
     avoient
    0.94
     dévelo
    0.93
     sauvages
    0.93
     sanitaires
    0.91
     étoient
    0.91
     anún
    0.90
     vertes
    0.89
     culoare
    0.88
    Activations Density 0.419%

    No Known Activations