© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6978
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" preceded by, followed by, or in the vicinity of location names.

    oai_token-act-pair · gemini-2.0-flash

    Canada related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     يتيمه
    -0.76
     itſelf
    -0.70
    URLException
    -0.69
     ainfi
    -0.68
    WebServlet
    -0.68
    issauga
    -0.67
     illustrazione
    -0.66
     kyse
    -0.66
     îna
    -0.66
     ceramica
    -0.66
    POSITIVE LOGITS
    //
    0.47
    AnchorStyles
    0.44
     تضيفلها
    0.44
    omitempty
    0.43
    iod
    0.42
     Hat
    0.42
     AssemblyTitle
    0.41
    europa
    0.39
     blo
    0.39
    NAMESPACE
    0.39
    Activations Density 1.713%

    No Known Activations