© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3702
    Prev
    Next
    INDEX
    Explanations

    words related to lifestyle, health, or how to live your life

    oai_token-act-pair · gemini-2.0-flash

    living

    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
    igi
    -0.52
    himovic
    -0.48
    weg
    -0.44
    ruk
    -0.44
     tích
    -0.44
    www
    -0.43
     Bes
    -0.42
     www
    -0.42
    ровку
    -0.42
    nsis
    -0.41
    POSITIVE LOGITS
     living
    2.39
    living
    2.14
     Living
    1.95
    Living
    1.95
     LIVING
    1.86
    LIVING
    1.64
     viviendo
    1.18
     liv
    1.13
     vivir
    1.02
     vivant
    0.97
    Activations Density 1.851%

    No Known Activations