© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5092
    Prev
    Next
    INDEX
    Explanations

    words and short phrases in French, often in a technical context

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
     É
    -0.61
     à
    -0.57
     À
    -0.56
     Rodríguez
    -0.56
    vé
    -0.56
     kā
    -0.55
     Á
    -0.55
     să
    -0.55
     å
    -0.54
    pé
    -0.54
    POSITIVE LOGITS
     jScrollPane
    0.54
     Monfieur
    0.52
    ".
    0.52
    ]));
    0.48
     gainera
    0.45
    yaszt
    0.44
    ựng
    0.43
    ưới
    0.43
    ']))
    0.42
     ―――――
    0.42
    Activations Density 2.000%

    No Known Activations