© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15485
    Prev
    Next
    INDEX
    Explanations

    words suggesting popularity or status and/or words related to writing, money, or babies

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    StructEnd
    -0.77
    GraphicsUnit
    -0.62
    الإنجليزية
    -0.60
    baby
    -0.60
    openConnection
    -0.60
    endphp
    -0.59
     baby
    -0.57
     تعدى
    -0.56
    ecap
    -0.55
     ***!
    -0.53
    POSITIVE LOGITS
     kit
    0.71
     swee
    0.56
    Kit
    0.52
     Kit
    0.50
    kit
    0.50
    şört
    0.50
    umptions
    0.49
    Links
    0.49
    ys
    0.48
    ̈́
    0.47
    Activations Density 5.745%

    No Known Activations