© 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. 3068
    Prev
    Next
    INDEX
    Explanations

    words related to positive sentiment and appreciation towards people

    oai_token-act-pair · gemini-2.0-flash

    Respect and emotional language

    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
    mpo
    -0.53
     $#
    -0.51
    Demografia
    -0.51
    ondissement
    -0.50
    ноз
    -0.50
    衛門
    -0.49
    ...
    -0.48
    atosis
    -0.48
    HasForeignKey
    -0.48
     rent
    -0.48
    POSITIVE LOGITS
    <bos>
    0.81
     wikipagina
    0.77
     plufieurs
    0.75
     sauvages
    0.74
    __(/*!
    0.74
     eenig
    0.74
     étoient
    0.72
     avoient
    0.71
     feroit
    0.70
     ainfi
    0.70
    Activations Density 0.835%

    No Known Activations