© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3376
    Prev
    Next
    INDEX
    Explanations

    words referring to family members or rulers

    oai_token-act-pair · gemini-2.0-flash

    family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     anaknya
    -0.76
     Daughters
    -0.74
    Daughter
    -0.72
     Daughter
    -0.72
     grandson
    -0.71
     CreateTagHelper
    -0.70
     daughters
    -0.70
     grandsons
    -0.69
     sons
    -0.67
     granddaughter
    -0.67
    POSITIVE LOGITS
    ‿
    0.55
    ниципа
    0.55
    pakking
    0.51
     synch
    0.51
    Geografie
    0.50
    TagHelper
    0.50
    expandindo
    0.49
     sauvages
    0.48
    Estás
    0.48
     */;
    0.48
    Activations Density 3.599%

    No Known Activations