© 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. 13498
    Prev
    Next
    INDEX
    Explanations

    words that show the degree or intensity of something

    oai_token-act-pair · gemini-2.0-flash

    emphasis

    np_max-act · gemini-2.0-flash

    very

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
     "
    -0.57
     Her
    -0.56
     an
    -0.55
     di
    -0.54
     her
    -0.53
     a
    -0.52
     non
    -0.52
     von
    -0.52
     v
    -0.51
     «
    -0.51
    POSITIVE LOGITS
     Theſe
    1.05
     Monfieur
    0.96
     feroit
    0.96
     Houſe
    0.92
     auroit
    0.90
     fédé
    0.90
     Reſ
    0.87
     Cæsar
    0.87
     aikaa
    0.87
     Shakspeare
    0.86
    Activations Density 1.448%

    No Known Activations