© 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. 235623
    Prev
    Next
    INDEX
    Explanations

    Si, else, proceed

    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
    γραφή
    0.39
     вторая
    0.35
    ᓘ
    0.35
     વેબસ
    0.35
     webcast
    0.35
     पड़ेंगे
    0.34
     second
    0.34
     তৃত
    0.34
     verge
    0.34
     மற
    0.34
    POSITIVE LOGITS
    =\$
    0.40
    тивних
    0.38
    viamente
    0.38
    ₅
    0.37
    䤚
    0.37
    йович
    0.36
    畽
    0.35
     energii
    0.35
    のは
    0.35
     ressources
    0.35
    Activations Density 0.001%

    No Known Activations