© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1457
    Prev
    Next
    INDEX
    Explanations

    Latin-derived taxonomic names and the phrase "De nova stella"

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    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
     pinulongan
    -0.63
    RuleContext
    -0.61
    ########.
    -0.58
     MEP
    -0.56
     '\\;'
    -0.54
    RunWith
    -0.54
    ControllerAdvice
    -0.52
    :+:
    -0.52
    idopsis
    -0.52
    AccessorTable
    -0.51
    POSITIVE LOGITS
     supérieurs
    0.59
     stället
    0.57
     möjlighet
    0.56
     igång
    0.55
     ögon
    0.55
     säll
    0.55
     vœux
    0.55
     démocratie
    0.55
     élas
    0.54
     exteriores
    0.54
    Activations Density 0.107%

    No Known Activations