© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2928
    Prev
    Next
    INDEX
    Explanations

    the word "minority"

    oai_token-act-pair · gemini-2.0-flash

    minority

    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
    Negative Logits
     in
    -0.88
     at
    -0.72
     as
    -0.68
     on
    -0.65
     under
    -0.64
     still
    -0.64
     across
    -0.63
     the
    -0.62
     into
    -0.62
     her
    -0.61
    POSITIVE LOGITS
     edifice
    0.84
     Alva
    0.83
     astray
    0.82
     mobilisation
    0.82
     seniority
    0.82
     hibernation
    0.81
    WindowConstants
    0.81
     mobilization
    0.81
     bunkers
    0.81
     mobilize
    0.79
    Activations Density 1.681%

    No Known Activations