© 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. 9306
    Prev
    Next
    INDEX
    Explanations

    the word "crisis" and words that are sometimes associated with it like "government" and "altruistic"

    oai_token-act-pair · gemini-2.0-flash

    crisis

    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
     Efq
    -1.11
     Jefus
    -1.09
     photolibrary
    -1.09
     Reſ
    -1.07
     myſelf
    -1.05
    بوابة
    -1.03
     Houſe
    -1.03
     ARXIV
    -1.03
     itſelf
    -1.02
     ་་
    -1.00
    POSITIVE LOGITS
    s
    0.76
     the
    0.75
    ,
    0.72
    _
    0.65
     you
    0.63
      
    0.61
     our
    0.60
    os
    0.59
    <strong>
    0.59
    ks
    0.58
    Activations Density 1.335%

    No Known Activations