© 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. 13326
    Prev
    Next
    INDEX
    Explanations

    Greek letters, especially when associated with the word "Greek"

    oai_token-act-pair · gemini-2.0-flash

    Greek language/math symbols

    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
     propOrder
    -0.65
     precisione
    -0.60
     tasche
    -0.60
     χρήση
    -0.59
     OFDb
    -0.59
    _;
    -0.57
     προϊόν
    -0.57
    tamol
    -0.57
    RetentionPolicy
    -0.56
    __':
    -0.56
    POSITIVE LOGITS
    RectangleBorder
    0.59
    δά
    0.51
    φέ
    0.51
    γραφ
    0.47
    πά
    0.44
    βά
    0.43
    enumi
    0.43
    γρά
    0.43
    κά
    0.42
    nagel
    0.42
    Activations Density 0.216%

    No Known Activations