© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14512
    Prev
    Next
    INDEX
    Explanations

    the word "foods"

    oai_token-act-pair · gemini-2.0-flash

    foods

    np_max-act · gemini-2.0-flash

    foods

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nakalista
    -1.03
     Paglinawan
    -0.97
    WithIOException
    -0.93
     Alcott
    -0.84
    oa̍t
    -0.84
     betweenstory
    -0.81
     <<<<<<<<<<<<<<
    -0.79
     EconPapers
    -0.77
     Spisak
    -0.76
    __((
    -0.75
    POSITIVE LOGITS
    gnition
    0.81
    polation
    0.79
    æus
    0.74
    ENEFITS
    0.72
    iſt
    0.71
    haustible
    0.70
    ercises
    0.69
    structor
    0.68
    drawal
    0.68
    ricus
    0.64
    Activations Density 1.443%

    No Known Activations