© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 271
    Prev
    Next
    INDEX
    Explanations

    bit manipulation

    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_44_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
    Standard
    0.41
     Standard
    0.38
     nd
    0.37
     mph
    0.37
    Ordinary
    0.37
    <0xC2>
    0.36
     Cass
    0.36
    Bob
    0.36
    mph
    0.36
     ayatan
    0.35
    POSITIVE LOGITS
     패턴
    0.44
     coaster
    0.38
     длиной
    0.38
     벡터
    0.38
     पैटर्न
    0.38
    patterns
    0.37
     Narc
    0.36
     柄
    0.36
     Pue
    0.36
     vacaciones
    0.36
    Activations Density 0.051%

    No Known Activations