© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6730
    Prev
    Next
    INDEX
    Explanations

    scientific text about the classification of species

    oai_token-act-pair · gemini-2.0-flash

    Species or franchise

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    OKER
    -0.48
    PMailer
    -0.48
    RenderAtEndOf
    -0.45
     فريبيس
    -0.45
    rawDesc
    -0.44
    crí
    -0.44
    RefreshLayout
    -0.43
    keyColumn
    -0.43
     koo
    -0.42
    енча
    -0.42
    POSITIVE LOGITS
     species
    1.19
     franchise
    1.12
    franchise
    0.98
    species
    0.97
     franchises
    0.93
     Species
    0.93
    Franchise
    0.90
    Species
    0.90
     Franchise
    0.88
    pecies
    0.87
    Activations Density 1.300%

    No Known Activations