© 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. 589
    Prev
    Next
    INDEX
    Explanations

    references to Christian religious texts and ideas

    oai_token-act-pair · gemini-2.0-flash

    religious 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
    FundMe
    -0.70
    didSet
    -0.70
    ResponseWriter
    -0.69
     god
    -0.68
    etCode
    -0.66
     OkHttpClient
    -0.65
    InstanceState
    -0.62
    estacks
    -0.62
     ElementRef
    -0.62
     lópez
    -0.60
    POSITIVE LOGITS
    enumi
    0.54
     defaultstate
    0.51
    He
    0.48
     He
    0.46
     supposes
    0.46
    ORING
    0.44
     Origen
    0.44
    ajur
    0.43
     esteem
    0.42
     причине
    0.42
    Activations Density 9.821%

    No Known Activations