© 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. 5472
    Prev
    Next
    INDEX
    Explanations

    words relating to systems and processes whether governmental, medical, or computer-related.

    oai_token-act-pair · gemini-2.0-flash

    HTML/code snippets

    np_max-act-logits · gemini-2.0-flash

    say "sentence punctuation"

    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_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
     Monfieur
    -0.57
    省市镇
    -0.56
     createState
    -0.54
    resizingMask
    -0.52
     fevere
    -0.51
     neceff
    -0.47
     fufficient
    -0.46
     contextLoads
    -0.46
     Majefty
    -0.45
     мәгълү
    -0.45
    POSITIVE LOGITS
    ”)
    1.54
    "}
    1.46
    </b>
    1.45
    </h2>
    1.44
    ")
    1.43
    ")}
    1.43
    ”),
    1.37
    ”).
    1.36
    </u>
    1.36
    </strong>
    1.36
    Activations Density 28.621%

    No Known Activations