© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1720
    Prev
    Next
    INDEX
    Explanations

    terms that describe headaches

    oai_token-act-pair · gemini-2.0-flash

    terms related to headache pain

    np_token-act-pair-logits · gpt-4o-mini

    pain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     OMITBAD
    -0.63
    httphttps
    -0.58
    новништво
    -0.57
     Ressource
    -0.51
    Бар
    -0.48
     snippetHide
    -0.48
     Reptile
    -0.48
    Халык
    -0.48
     PCV
    -0.47
    arrête
    -0.47
    POSITIVE LOGITS
     pain
    1.14
     Pain
    0.97
    pain
    0.96
    Pain
    0.95
     ache
    0.92
     pains
    0.91
     painful
    0.88
     PAIN
    0.87
     hurts
    0.84
     pained
    0.76
    Activations Density 1.493%

    No Known Activations