© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83731
    Prev
    Next
    INDEX
    Explanations

    after September 2021

    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_23_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
     Files
    0.38
     Flu
    0.37
     ಸ
    0.37
     Prime
    0.37
     Mouth
    0.37
     Cree
    0.36
    addock
    0.36
     trama
    0.36
     silo
    0.36
    ಣ
    0.35
    POSITIVE LOGITS
    媝
    0.42
     grief
    0.41
     blessings
    0.41
     Août
    0.40
     categorias
    0.40
     eo
    0.39
     eloquent
    0.38
     disgusted
    0.38
    كمال
    0.38
     utu
    0.38
    Activations Density 0.004%

    No Known Activations