© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209561
    Prev
    Next
    INDEX
    Explanations

    number is sum

    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_25_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
    OPH
    0.37
     terlebih
    0.35
    orno
    0.34
    rar
    0.32
     dare
    0.31
     Stell
    0.31
    ammens
    0.31
    窍
    0.31
     সম্প্র
    0.31
     दाम
    0.30
    POSITIVE LOGITS
    🕕
    0.42
    ફેદ
    0.42
     ética
    0.41
     रिश्
    0.40
    ेक्स
    0.40
     fárm
    0.37
    導致
    0.36
     planilha
    0.36
     emocional
    0.35
     कर्मियों
    0.35
    Activations Density 0.001%

    No Known Activations