© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15450
    Prev
    Next
    INDEX
    Explanations

    words related to medical trials, political commentary and the history of slavery

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    IBOutlet
    -0.47
     Al
    -0.44
    Personensuche
    -0.42
    uca
    -0.42
    ут
    -0.42
     ha
    -0.42
    帽
    -0.41
    Informa
    -0.41
    u
    -0.40
     AssemblyProduct
    -0.40
    POSITIVE LOGITS
     Majefty
    0.90
    ")));
    0.80
    ſelves
    0.79
     purpoſe
    0.77
     deſt
    0.76
     الرياضيه
    0.75
    ſelf
    0.75
    ]<<"
    0.74
     pleaſure
    0.74
     Reſ
    0.73
    Activations Density 7.892%

    No Known Activations