© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10125
    Prev
    Next
    INDEX
    Explanations

    a mix of seemingly unrelated things, including parts of numbers and place names and names of organizations.

    oai_token-act-pair · gemini-2.0-flash

    possibly foreign words

    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
     disambiguazione
    -0.98
     estekak
    -0.97
    contentLoaded
    -0.97
     CreateTagHelper
    -0.91
    AndEndTag
    -0.81
    parsedMessage
    -0.80
    ंदीखरीदारी
    -0.78
    kloped
    -0.77
     виправивши
    -0.75
    RectangleBorder
    -0.75
    POSITIVE LOGITS
     lää
    0.59
     sähkö
    0.59
     hyö
    0.56
     aikaa
    0.55
     ympä
    0.54
     kesk
    0.54
    +#+
    0.54
     julk
    0.53
     lämp
    0.53
     medu
    0.52
    Activations Density 0.442%

    No Known Activations