© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10737
    Prev
    Next
    INDEX
    Explanations

    mentions of friends and family along with related words like "team" and "support"

    oai_token-act-pair · gemini-2.0-flash

    Friends and neighbors

    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
    GEBURTS
    -0.52
     виправивши
    -0.49
    ريكية
    -0.49
    tral
    -0.48
    ReusableCell
    -0.48
    исленность
    -0.47
    revet
    -0.47
    Unders
    -0.47
     BorderLayout
    -0.47
    '],
    -0.47
    POSITIVE LOGITS
     friends
    0.92
     neighbours
    0.81
     neighbors
    0.80
     friend
    0.79
     FRIENDS
    0.75
    friends
    0.73
    Friends
    0.73
     neighbor
    0.72
     vrienden
    0.71
     neighbour
    0.70
    Activations Density 2.334%

    No Known Activations