© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14539
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to crafting, especially sewing and family history

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RTLD
    -0.53
     tslint
    -0.52
     PSF
    -0.51
    complexContent
    -0.50
     ModelAndView
    -0.50
     eyel
    -0.50
     corruption
    -0.49
    TRIBUN
    -0.49
     Tiss
    -0.49
     virkelig
    -0.49
    POSITIVE LOGITS
     mom
    0.79
     son
    0.70
     Mom
    0.68
     Dad
    0.68
     him
    0.66
     dad
    0.66
    oredCriteria
    0.64
    mom
    0.64
     my
    0.61
     his
    0.61
    Activations Density 51.145%

    No Known Activations