© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10765
    Prev
    Next
    INDEX
    Explanations

    mentions of health-related government departments and councils

    oai_token-act-pair · gemini-2.0-flash

    town council

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     frequenza
    -0.51
    mender
    -0.48
    frequency
    -0.48
     fréquence
    -0.47
     frecuencia
    -0.45
     lisäksi
    -0.45
     Chancery
    -0.45
    Frequency
    -0.45
     frequency
    -0.45
     Frequency
    -0.44
    POSITIVE LOGITS
     OFDb
    0.79
    WithIOException
    0.77
    principalColumn
    0.65
     kiệm
    0.59
     newList
    0.59
     mergeFrom
    0.59
    |}{$
    0.56
    yntaxException
    0.56
    Izvori
    0.56
     tfsi
    0.55
    Activations Density 0.666%

    No Known Activations