© 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. 1775
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    oai_token-act-pair · gemini-2.0-flash

    the word 'perfect'

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

    perfect

    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
     réglable
    -0.58
     beſt
    -0.57
     fufficient
    -0.55
     bäst
    -0.55
    stands
    -0.55
     excelentes
    -0.54
    Standing
    -0.54
     faſt
    -0.52
     corretamente
    -0.52
     good
    -0.51
    POSITIVE LOGITS
    encodeWith
    0.77
     mergeFrom
    0.77
    хьтан
    0.62
     ComVisible
    0.62
    XMLSchema
    0.60
     newOwner
    0.60
    URLException
    0.59
    NameInMap
    0.59
    SharedDtor
    0.58
     useAppContext
    0.57
    Activations Density 2.053%

    No Known Activations