© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7758
    Prev
    Next
    INDEX
    Explanations

    how to keep a dog occupied

    oai_token-act-pair · gemini-2.0-flash

    pets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     vet
    -1.05
     vets
    -0.98
     Vet
    -0.84
    vet
    -0.80
    Vet
    -0.80
     VET
    -0.77
    VET
    -0.72
     Waray
    -0.63
     Paglinawan
    -0.63
    AnchorStyles
    -0.62
    POSITIVE LOGITS
    FilterChain
    0.54
    setDo
    0.45
    iama
    0.43
     Cune
    0.43
    وائد
    0.41
     Science
    0.40
    Demo
    0.40
    蚪
    0.39
     SCIENCE
    0.39
    omore
    0.39
    Activations Density 1.791%

    No Known Activations