© 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. 9853
    Prev
    Next
    INDEX
    Explanations

    the word "either" and words that appear with frequency in proper names

    oai_token-act-pair · gemini-2.0-flash

    either

    np_max-act · gemini-2.0-flash
    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
    <bos>
    -1.13
    y
    -0.91
    e
    -0.90
    l
    -0.90
    i
    -0.81
    u
    -0.80
    o
    -0.79
     تضيفلها
    -0.77
    es
    -0.77
    er
    -0.77
    POSITIVE LOGITS
    ^(@)
    0.76
    aternary
    0.72
     payé
    0.71
    iyaki
    0.66
    HideFlags
    0.65
    ']")
    0.64
    équences
    0.63
    Πηγή
    0.62
     canela
    0.61
    gebob
    0.61
    Activations Density 2.443%

    No Known Activations