© 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. 9434
    Prev
    Next
    INDEX
    Explanations

    the word "tough" and words/concepts related to difficulty

    oai_token-act-pair · gemini-2.0-flash

    tough

    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
    m
    -0.69
    is
    -0.69
    \\
    -0.68
    ​
    -0.67
     av
    -0.66
    ly
    -0.64
    con
    -0.63
     con
    -0.63
    de
    -0.61
    -0.61
    POSITIVE LOGITS
     sauvages
    1.45
     vectorielles
    1.40
     dévelo
    1.37
     pouvoit
    1.36
     feroit
    1.33
     auroit
    1.31
     commerciaux
    1.30
     Monfieur
    1.30
     étoit
    1.30
     themſelves
    1.29
    Activations Density 2.125%
    No Known Activations