© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46264
    Prev
    Next
    INDEX
    Explanations

    code as string or data

    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_22_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
    農
    0.37
     pesto
    0.34
    ixos
    0.33
     guacamole
    0.33
    农
    0.32
     Perfectly
    0.32
    കെ
    0.31
     Seç
    0.31
     chiếc
    0.31
     음식
    0.31
    POSITIVE LOGITS
    ለ
    0.32
    Injection
    0.32
    Normal
    0.31
     അട
    0.31
    区块
    0.31
     পর্যন্ত
    0.30
    EmbeddedResource
    0.30
     حداقل
    0.30
     والح
    0.30
    pre
    0.30
    Activations Density 0.095%

    No Known Activations