© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40753
    Prev
    Next
    INDEX
    Explanations

    sour cream, honey, or food dishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    r
    1.13
    t
    0.91
    m
    0.84
    f
    0.82
    en
    0.76
    ah
    0.75
    ant
    0.73
    he
    0.73
    all
    0.71
    ih
    0.71
    POSITIVE LOGITS
     to
    0.79
    \
    0.66
    >
    0.64
    也
    0.64
     the
    0.61
    </h3>
    0.61
    ่
    0.60
     interpre
    0.59
    ]){
    0.57
    B
    0.56
    Activations Density 0.006%

    No Known Activations