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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4863
    Prev
    Next
    INDEX
    Explanations

    references to religious doctrine

    oai_token-act-pair · gemini-2.0-flash

    religious texts/values

    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
    TypedDataSet
    -0.71
    sizeCache
    -0.65
    enderror
    -0.63
     оригіналу
    -0.62
     дописавши
    -0.61
    rawDesc
    -0.59
    istoitu
    -0.59
     Мексичка
    -0.57
     FetchType
    -0.57
     createSprite
    -0.56
    POSITIVE LOGITS
     ordinaria
    0.50
    lň
    0.45
    cript
    0.44
     Sociales
    0.43
     Mark
    0.43
    adell
    0.43
    üedad
    0.43
    WHEREAS
    0.42
     script
    0.41
    laterra
    0.40
    Activations Density 3.441%

    No Known Activations