© 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. 5597
    Prev
    Next
    INDEX
    Explanations

    words that are in the context of parent-child relationships

    oai_token-act-pair · gemini-2.0-flash

    family relationships

    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
     extension
    -0.52
     Extension
    -0.52
    rubin
    -0.50
     Walkover
    -0.50
     gawas
    -0.49
    дан
    -0.48
    Wut
    -0.47
    ATU
    -0.46
    Extension
    -0.46
    Extend
    -0.46
    POSITIVE LOGITS
     Rhys
    0.58
     Aar
    0.54
    nitive
    0.53
     незавершена
    0.52
    STATES
    0.52
    PropertyGroup
    0.52
    [])
    0.50
    runApp
    0.50
    stateProvider
    0.49
    Pfe
    0.49
    Activations Density 6.967%

    No Known Activations