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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8536
    Prev
    Next
    INDEX
    Explanations

    words that are important to research papers.

    oai_token-act-pair · gemini-2.0-flash

    Scientific/Technical text

    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
     stället
    -0.57
     tremp
    -0.52
     préférences
    -0.52
     Compatible
    -0.49
    addComponent
    -0.49
     lentes
    -0.48
    rungsseite
    -0.47
     compatible
    -0.47
     préféré
    -0.46
     paradiso
    -0.46
    POSITIVE LOGITS
    esgue
    0.72
     jspb
    0.63
    calipsis
    0.62
    ousine
    0.61
    argout
    0.60
    afficheront
    0.60
    abetes
    0.57
     said
    0.56
    jspb
    0.55
    yntaxException
    0.54
    Activations Density 15.847%

    No Known Activations