© 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. 85358
    Prev
    Next
    INDEX
    Explanations

    -ologist suffix

    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
    s
    0.95
    </h3>
    0.92
    ه
    0.89
    m
    0.85
    ↵
    0.80
    不
    0.70
    不满
    0.70
    仍在
    0.70
    不必
    0.68
    不可以
    0.68
    POSITIVE LOGITS
    یم
    0.98
    行う
    0.92
    ری
    0.88
    ید
    0.88
    ang
    0.80
    یر
    0.77
    یت
    0.76
    ગી
    0.75
    لی
    0.73
    )]),
    0.73
    Activations Density 0.006%

    No Known Activations