© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205575
    Prev
    Next
    INDEX
    Explanations

    New York, New Jersey, New Delhi, New Haven

    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_20_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
    ೊಂದಿಗೆ
    0.18
    ams
    0.17
    ımı
    0.17
    amed
    0.16
    ract
    0.15
     ಅದನ್ನು
    0.15
    䟧
    0.15
    $/,
    0.15
     आगामी
    0.15
    Untitled
    0.15
    POSITIVE LOGITS
     cavity
    0.18
     glitch
    0.18
     phosphorus
    0.18
     gaps
    0.17
     percolation
    0.17
     éc
    0.17
     gap
    0.16
     flange
    0.16
     loophole
    0.16
     cav
    0.16
    Activations Density 0.006%

    No Known Activations