© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219500
    Prev
    Next
    INDEX
    Explanations

    bad

    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_47_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
    බැ
    0.47
    ニック
    0.39
    蛔
    0.38
    甲方
    0.38
    負
    0.37
    '">
    0.37
     ጋ
    0.37
    '`--
    0.36
    乙方
    0.36
     अध्या
    0.36
    POSITIVE LOGITS
     machinery
    0.41
    count
    0.38
    চ্চ
    0.38
    তন্ত্র
    0.37
     Machinery
    0.37
    timestep
    0.37
    ake
    0.37
    हली
    0.36
    encoded
    0.36
    Encoding
    0.36
    Activations Density 0.002%

    No Known Activations