© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12325
    Prev
    Next
    INDEX
    Explanations

    descriptions of family

    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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    grand
    -1.10
     grand
    -1.09
    Grand
    -1.05
     GRAND
    -1.05
     Grand
    -1.05
    GRAND
    -0.97
     grandparents
    -0.96
     grandfather
    -0.87
     grandpa
    -0.86
     grandma
    -0.85
    POSITIVE LOGITS
     daughter
    0.87
    RenderAtEndOf
    0.85
     Meksiku
    0.84
     NSCoder
    0.82
    AndEndTag
    0.81
    sizeCache
    0.79
     nahilalakip
    0.78
     CreateTagHelper
    0.75
    fjspx
    0.75
     otomatig
    0.74
    Activations Density 0.259%

    No Known Activations