© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14560
    Prev
    Next
    INDEX
    Explanations

    a mix of German and English language grammar and writing-related terms.

    oai_token-act-pair · gemini-2.0-flash

    German language

    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
    Jährige
    -0.70
    bcryptjs
    -0.69
     myſelf
    -0.68
     uſed
    -0.68
     themſelves
    -0.63
    IonicModule
    -0.63
     ſtate
    -0.63
    Jäh
    -0.62
     himſelf
    -0.62
     ſur
    -0.61
    POSITIVE LOGITS
    */
    0.60
    webElement
    0.60
     mergeFrom
    0.59
    unknownFields
    0.56
     <>",
    0.56
    BSITE
    0.54
    });
    0.51
     “
    0.50
     i
    0.49
    اریخ
    0.48
    Activations Density 1.729%

    No Known Activations