© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5128
    Prev
    Next
    INDEX
    Explanations

    words and clauses relating to interpersonal relationships

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     <<<<<<<<<<<<<<
    -0.83
     Paglinawan
    -0.61
     Anche
    -0.52
     flesta
    -0.52
     protoimpl
    -0.50
    webElementXpaths
    -0.49
     automatiques
    -0.49
     colorés
    -0.48
     normaux
    -0.48
     amarela
    -0.48
    POSITIVE LOGITS
     >=",
    0.64
    uaire
    0.60
    发表于
    0.57
    पया
    0.57
    ⓧ
    0.56
     שוליים
    0.56
    DeleteBehavior
    0.55
     kasarigan
    0.55
     NgModule
    0.54
    AccessorTable
    0.54
    Activations Density 29.933%

    No Known Activations