© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254182
    Prev
    Next
    INDEX
    Explanations

    say "ropolis" or "ropolitan"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    maur
    0.40
    শ্ব
    0.37
    heure
    0.36
     asymmetry
    0.36
    zäh
    0.35
     dignitaries
    0.35
    ('/:
    0.34
    ഗാ
    0.34
    lone
    0.34
    𝗨
    0.34
    POSITIVE LOGITS
     поли
    0.53
     ac
    0.47
     Поли
    0.47
    ırl
    0.46
    როს
    0.46
     Ak
    0.45
     ác
    0.45
    ることができる
    0.43
     Ac
    0.43
    りを
    0.43
    Activations Density 0.000%

    No Known Activations