© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14938
    Prev
    Next
    INDEX
    Explanations

    jargon from a variety of subject areas, including computer programming, electronics, and general business terminology

    oai_token-act-pair · gemini-2.0-flash

    programming symbols/abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Vidite
    -0.76
     فريبيس
    -0.73
    Xna
    -0.62
     coronavirus
    -0.61
    хьтан
    -0.61
    regate
    -0.59
    onaise
    -0.59
     Савезне
    -0.58
     lenker
    -0.58
    cipline
    -0.58
    POSITIVE LOGITS
     poveznice
    0.55
     prolly
    0.53
     تانيه
    0.51
     Xmas
    0.46
     @
    0.45
     hubby
    0.45
     Dems
    0.44
     spé
    0.42
     Nativity
    0.42
    <bos>
    0.41
    Activations Density 1.438%

    No Known Activations