© 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. 12760
    Prev
    Next
    INDEX
    Explanations

    The neuron looks for the phrase "stay at the resorts". It also appears to activate strongly for language describing car safety information

    oai_token-act-pair · gemini-2.0-flash

    five

    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
    SequentialGroup
    -0.66
    存于互联网档案馆
    -0.66
    MLLoader
    -0.64
     coar
    -0.63
    Geplaatst
    -0.63
    ViewImports
    -0.60
    PickerController
    -0.59
    __":
    -0.59
     Himo
    -0.58
     SwitchCompat
    -0.57
    POSITIVE LOGITS
     five
    2.14
     Five
    1.86
    five
    1.86
    Five
    1.79
     cinq
    1.76
     FIVE
    1.75
     four
    1.63
     cinco
    1.63
    FIVE
    1.59
     Fünf
    1.57
    Activations Density 1.769%

    No Known Activations