© 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. 4867
    Prev
    Next
    INDEX
    Explanations

    German sentences regarding sentence construction

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    np_max-act-logits · 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
     und
    -1.27
     og
    -1.10
     och
    -1.08
     và
    -0.96
     dan
    -0.92
     és
    -0.90
    和
    -0.89
     和
    -0.87
     et
    -0.87
     en
    -0.86
    POSITIVE LOGITS
    
    0.56
     Roskov
    0.56
    ėte
    0.54
     Réponses
    0.52
     quelcon
    0.52
    imakasih
    0.49
     الرياضيه
    0.48
     desee
    0.48
    tagext
    0.47
    )_/¯
    0.47
    Activations Density 2.245%

    No Known Activations