© 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. 13527
    Prev
    Next
    INDEX
    Explanations

    words related to something negative balanced with words disputing it

    oai_token-act-pair · gemini-2.0-flash

    shame

    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
     Shakspeare
    -1.10
     rehearing
    -1.09
     oars
    -1.05
     weakest
    -1.05
     cowardice
    -1.05
     auroit
    -1.05
     strictest
    -1.05
     deadliest
    -1.05
     feroit
    -1.04
     Monfieur
    -1.04
    POSITIVE LOGITS
     for
    0.90
     in
    0.89
     to
    0.72
     not
    0.71
     as
    0.70
     at
    0.69
     de
    0.69
     from
    0.68
     des
    0.66
     on
    0.66
    Activations Density 1.876%

    No Known Activations