© 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. 205664
    Prev
    Next
    INDEX
    Explanations

    names and specific terms

    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
    '
    0.40
     para
    0.39
    ,
    0.39
    第五
    0.37
     della
    0.37
     Sur
    0.37
    形成
    0.36
    -
    0.36
     Over
    0.36
    第一
    0.36
    POSITIVE LOGITS
     marshm
    0.46
    టువంటి
    0.44
     ponú
    0.44
     metabolite
    0.42
     dialogo
    0.42
    aciju
    0.42
     extré
    0.41
     također
    0.41
    también
    0.41
     ப்ளாக்
    0.41
    Activations Density 0.000%

    No Known Activations