© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121531
    Prev
    Next
    INDEX
    Explanations

    no need to

    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_27_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
    Employer
    0.39
    Mul
    0.36
    Ongoing
    0.36
    Coord
    0.36
     totalement
    0.36
     employer
    0.34
     chuckle
    0.34
    범
    0.34
     diverses
    0.34
     opportune
    0.34
    POSITIVE LOGITS
    éticos
    0.37
    াধিকার
    0.37
    气质
    0.35
    枚举
    0.35
    咸
    0.34
    addSql
    0.34
    )?;
    0.33
     Lodge
    0.33
     Equival
    0.33
    了嗎
    0.33
    Activations Density 0.015%

    No Known Activations