© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    the word "opposition" and anything that might be connected to it such as resistance, campaign, party, or disagreement

    oai_token-act-pair · gemini-2.0-flash

    opposition

    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
    -0.79
    t
    -0.76
    or
    -0.73
    and
    -0.71
    ul
    -0.70
    k
    -0.70
    h
    -0.68
    al
    -0.66
    to
    -0.65
    at
    -0.65
    POSITIVE LOGITS
    AndEndTag
    1.13
     resourceCulture
    1.05
    othesis
    1.00
    
    1.00
     дописавши
    0.99
    allenges
    0.98
    uawei
    0.93
    drawal
    0.91
    iffance
    0.91
    arranty
    0.91
    Activations Density 1.846%

    No Known Activations