© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13002
    Prev
    Next
    INDEX
    Explanations

    mentions of "Japanese" and "Italian"

    oai_token-act-pair · gemini-2.0-flash

    countries

    np_max-act · gemini-2.0-flash

    nationalities

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Lithuanian
    -0.91
     Croatian
    -0.87
     Romanian
    -0.87
     griega
    -0.86
     Hungarian
    -0.86
     coreano
    -0.86
     Slovenian
    -0.84
     Bulgarian
    -0.84
     Ukrainian
    -0.83
    Mexican
    -0.81
    POSITIVE LOGITS
    <bos>
    1.02
    %</
    0.58
     country
    0.55
    Compat
    0.53
     central
    0.53
    <h1>
    0.52
     Pollack
    0.52
     America
    0.50
    ttemberg
    0.50
    -
    0.49
    Activations Density 0.723%

    No Known Activations