© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11747
    Prev
    Next
    INDEX
    Explanations

    use of terminology, especially jargon and slang

    oai_token-act-pair · gemini-2.0-flash

    Slang/Jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     opérateur
    -0.58
     feeders
    -0.48
    ﷺ
    -0.48
     OBB
    -0.47
     mattino
    -0.47
     "../../../
    -0.47
     propOrder
    -0.46
    okovic
    -0.46
     monarchs
    -0.45
     <-
    -0.45
    POSITIVE LOGITS
     term
    0.73
     terms
    0.65
     termes
    0.64
     terme
    0.63
    OSSARY
    0.62
     textStatus
    0.56
     Term
    0.56
    complexType
    0.56
    migrationBuilder
    0.56
    terms
    0.56
    Activations Density 0.722%

    No Known Activations