© 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. 1458
    Prev
    Next
    INDEX
    Explanations

    discourse markers and connectives, especially those that indicate logic, reasoning, and argumentation

    oai_token-act-pair · gemini-2.0-flash

    natural language

    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
     —
    -2.89
    —
    -2.34
     --
    -2.28
    ——
    -2.19
     ——
    -2.13
    --
    -2.09
    €”
    -2.03
     ―
    -1.98
    )—
    -1.91
    ―
    -1.91
    POSITIVE LOGITS
    VersionUID
    0.60
     Мексичка
    0.56
    \{\\
    0.55
    Schedulers
    0.52
    AddHtmlAttribute
    0.52
    databinding
    0.51
    WEBPACK
    0.48
     nawr
    0.48
    Diwedd
    0.47
    ...');
    0.47
    Activations Density 2.789%

    No Known Activations