© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5363
    Prev
    Next
    INDEX
    Explanations

    words frequently used in mathematical or technical papers

    oai_token-act-pair · gemini-2.0-flash

    say "$"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     (£
    -0.98
    </code>
    -0.89
    </u>
    -0.88
    </sub>
    -0.86
     (€
    -0.81
    }$$
    -0.80
    </h6>
    -0.80
    </s>
    -0.78
    "`
    -0.76
    </sup>
    -0.75
    POSITIVE LOGITS
     $
    1.21
    \\
    0.65
    .\\
    0.56
    :\\
    0.56
    \_
    0.54
    -\\
    0.52
    ?\\
    0.52
    \&
    0.49
    ,\\
    0.49
     $\&$
    0.48
    Activations Density 3.671%

    No Known Activations