© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176843
    Prev
    Next
    INDEX
    Explanations

    astronomical units (AU)

    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_20_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
     transition
    0.47
    圤
    0.47
    ្នក
    0.47
     agacch
    0.46
     Port
    0.46
    다라고
    0.45
     переход
    0.45
    ुली
    0.43
    निवास
    0.42
     existencia
    0.42
    POSITIVE LOGITS
    moja
    0.46
    Claudia
    0.43
    Après
    0.42
    ː
    0.41
    Noir
    0.40
     één
    0.40
     its
    0.40
    visor
    0.39
     Moj
    0.39
    cnpj
    0.39
    Activations Density 0.000%

    No Known Activations